BOP-ASK: Object-Interaction Reasoning for Vision-Language Models
Paper • 2511.16857 • Published
Datasets:
conversations list | images list | question_type string | question_subtype string | depths list | masks string | object_id unknown |
|---|---|---|---|---|---|---|
[
{
"from": "user",
"value": "<image>\nAre the pair of salad serving utensils positioned to the right of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the pairs of kitchen spatulas to the left of the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the salad serving utensils to the left of the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the salad serving utensils to the left of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the two pairs of kitchen spatulas positioned to the left of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the two pairs of kitchen spatulas to the left of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nAre the two pairs of kitchen spatulas to the right of the set of whisks? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nCan you provide the position (tx ty tz m) and the 3x3 rotation matrix (in row-major order) for the camera to world transformation? Your response should be a flattened 4x4 matrix, from row 1 to row 4 in a list."
},
{
"from": "gpt",
"value": "[[-0.46, 0.55, -0.... | [
"images/scene_000001_frame_000001.png"
] | camera | extrinsics | [] | null | null |
[
{
"from": "user",
"value": "<image>\nCan you provide the position (tx ty tz mm), scale (sx sy sz mm), and Euler XYZ angles (radians) for the two pairs of kitchen spatulas? Your response should be as position: [], scale: [], euler angles: []."
},
{
"from": "gpt",
"value": "position: [56.68, -131.... | [
"images/scene_000001_frame_000001.png"
] | pose | euler | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the left of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the left of the pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the left of the set of whisks used for mixing? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the left of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the right of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the right of the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the right of the two pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the collapsible silicone colander positioned to the right of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the cooking spoon with green colored heads and light wooden handles farther from the camera than the green colored whisk with a green handle?"
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | farther | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "10,37" |
[
{
"from": "user",
"value": "<image>\nIs the cooking spoon with green heads closer to the camera than the green whisk?"
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | closer | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "10,37" |
[
{
"from": "user",
"value": "<image>\nIs the cooking spoon with green heads positioned to the left of the green colored whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "10,37" |
[
{
"from": "user",
"value": "<image>\nIs the cooking spoon with the green heads positioned to the right of the green colored whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "10,37" |
[
{
"from": "user",
"value": "<image>\nIs the green colored colander closer to the camera than the whisk with the black handle and red wires?"
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | closer | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "34,39" |
[
{
"from": "user",
"value": "<image>\nIs the green colored colander farther from the camera than the whisk with the black handle and red wires?"
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | farther | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "34,39" |
[
{
"from": "user",
"value": "<image>\nIs the green colored colander positioned to the left of the whisk with a black handle and red wires? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "34,39" |
[
{
"from": "user",
"value": "<image>\nIs the green colored colander positioned to the right of the whisk with the black handle and red wires? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "34,39" |
[
{
"from": "user",
"value": "<image>\nIs the pair of kitchen spatulas positioned to the right of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of kitchen spatulas to the left of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of kitchen spatulas to the right of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of salad serving utensils positioned above the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of salad serving utensils positioned to the left of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of salad serving utensils positioned to the left of the two pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of salad serving utensils positioned to the right of the two pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the pair of salad serving utensils positioned to the right of the whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of kitchen spatulas positioned to the right of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks located below the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks positioned to the left of the pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks positioned to the right of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks positioned to the right of the two pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks to the left of the whisk used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks used for mixing ingredients in cooking and baking positioned to the right of the whisk kitchen tool? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks used for mixing ingredients positioned to the left of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the set of whisks used for mixing ingredients to the left of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the spatula with a pink head and wooden handle positioned to the left of the green colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,34" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle closer to the camera than the light green whisk with a light green handle?"
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | closer | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,37" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle closer to the camera than the whisk with the black handle and red wires?"
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | closer | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,39" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle farther from the camera than the green colander?"
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | farther | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,34" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle farther from the camera than the light green whisk with a light green handle?"
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | farther | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,37" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle farther from the camera than the whisk with the black handle and red wires?"
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | farther | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,39" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle positioned to the right of the light green whisk with a light green handle? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,37" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle to the left of the green whisk? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,37" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head and wooden handle to the right of the green colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,34" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head closer to the camera than the green colander?"
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | depth_relative | closer | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,34" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head located to the left of the whisk with the black handle? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,39" |
[
{
"from": "user",
"value": "<image>\nIs the spatula with the pink head to the right of the whisk that has a black handle and red wires? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | null | "27,39" |
[
{
"from": "user",
"value": "<image>\nIs the whisk located to the left of the salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk positioned to the left of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk positioned to the right of the collapsible silicone colander? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk positioned to the right of the pair of salad serving utensils? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk positioned to the right of the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk positioned to the right of the two pairs of kitchen spatulas with silicone heads? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk to the left of the set of whisks used for mixing ingredients? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "no"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nIs the whisk to the left of the two pairs of kitchen spatulas? Your response should be a single word: yes or no."
},
{
"from": "gpt",
"value": "yes"
}
] | [
"images/scene_000001_frame_000001.png"
] | spatial_reasoning | relative_position | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates for the cuboid corners of the pair of kitchen spatulas featuring smooth silicone heads and sturdy wooden handles? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates for the cuboid corners of the set of whisks used for mixing ingredients? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": "... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the collapsible silicone colander designed for draining liquids? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gp... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the cooking spoon with green heads and light wooden handles? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_obj_000010_mask.png | 10 |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the green whisk with a matching green handle? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": "[... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_obj_000037_mask.png | 37 |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the pair of salad serving utensils consisting of a slotted spoon and a solid spoon? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the spatula with a pink head and wooden handle? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": ... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_obj_000027_mask.png | 27 |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the whisk with a black handle and red wires? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": "[[... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_obj_000039_mask.png | 39 |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners for the whisk, the kitchen tool designed for mixing ingredients? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 2-D pixel coordinates of the cuboid corners pertaining to the green colored colander? Your response should be a list of 2D X,Y coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": "[[1312, 1... | [
"images/scene_000001_frame_000001.png"
] | pose | 2dbbox | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_obj_000034_mask.png | 34 |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 3-D coordinates (x in pixel, y in pixel, z depth in mm) for the cuboid corners of the pair of salad serving utensils? Your response should be a list of 3D X,Y,Z coordinates with bottom face first then top face, all counter-clockwise."
},
{
"fro... | [
"images/scene_000001_frame_000001.png"
] | pose | 3dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 3-D coordinates (x in pixel, y in pixel, z depth in mm) of the cuboid corners for the collapsible silicone colander? Your response should be a list of 3D X,Y,Z coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from... | [
"images/scene_000001_frame_000001.png"
] | pose | 3dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 3-D coordinates (x in pixel, y in pixel, z depth in mm) of the cuboid corners for the set of whisks used in cooking and baking? Your response should be a list of 3D X,Y,Z coordinates with bottom face first then top face, all counter-clockwise."
},
... | [
"images/scene_000001_frame_000001.png"
] | pose | 3dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 3-D coordinates (x in pixel, y in pixel, z depth in mm) of the cuboid corners for the two pairs of kitchen spatulas? Your response should be a list of 3D X,Y,Z coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from... | [
"images/scene_000001_frame_000001.png"
] | pose | 3dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the eight 3-D coordinates (x in pixel, y in pixel, z depth in mm) of the cuboid corners for the whisk? Your response should be a list of 3D X,Y,Z coordinates with bottom face first then top face, all counter-clockwise."
},
{
"from": "gpt",
"value": "... | [
"images/scene_000001_frame_000001.png"
] | pose | 3dbbox | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and Euler XYZ angles (radians) for the collapsible silicone colander? Your response should be as position: [], scale: [], euler angles: []."
},
{
"from": "gpt",
"value": "position: [69.21, 95.7, 1079.5... | [
"images/scene_000001_frame_000001.png"
] | pose | euler | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and Euler XYZ angles (radians) for the pair of salad serving utensils? Your response should be as position: [], scale: [], euler angles: []."
},
{
"from": "gpt",
"value": "position: [-142.06, -220.31, ... | [
"images/scene_000001_frame_000001.png"
] | pose | euler | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and Euler XYZ angles (radians) for the set of whisks used in cooking and baking? Your response should be as position: [], scale: [], euler angles: []."
},
{
"from": "gpt",
"value": "position: [-135.79,... | [
"images/scene_000001_frame_000001.png"
] | pose | euler | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and the 3x3 rotation matrix (row-major) for the collapsible silicone colander? Your response should be as position: [], scale: [], rotation matrix: []."
},
{
"from": "gpt",
"value": "position: [69.21, ... | [
"images/scene_000001_frame_000001.png"
] | pose | matrix | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and the 3x3 rotation matrix (row-major) for the set of whisks used in cooking and baking? Your response should be as position: [], scale: [], rotation matrix: []."
},
{
"from": "gpt",
"value": "positio... | [
"images/scene_000001_frame_000001.png"
] | pose | matrix | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat are the position (tx ty tz mm), scale (sx sy sz mm), and the 3x3 rotation matrix (row-major) for the whisk used for mixing ingredients? Your response should be as position: [], scale: [], rotation matrix: []."
},
{
"from": "gpt",
"value": "position: [-47... | [
"images/scene_000001_frame_000001.png"
] | pose | matrix | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path required to move the set of whisks to the location of the two pairs of kitchen spatulas? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"v... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the collapsible silicone colander to the location of the pair of salad serving utensils? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt"... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the collapsible silicone colander to the location of the two pairs of kitchen spatulas? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the cooking spoon with green heads to the location of the green colored colander? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_10_mask.png,masks/scene_000001_frame_000001_goal_34_mask.png | "10,34" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the cooking spoon with green heads to the location of the green whisk? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "pa... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_10_mask.png,masks/scene_000001_frame_000001_goal_37_mask.png | "10,37" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the cooking spoon with green heads to the location of the whisk with a black handle and red wires? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"fr... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_10_mask.png,masks/scene_000001_frame_000001_goal_39_mask.png | "10,39" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the green colored colander to the location of the cooking spoon with green heads and light wooden handles? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_34_mask.png,masks/scene_000001_frame_000001_goal_10_mask.png | "34,10" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the green colored colander to the location of the green colored whisk with the green handle? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_34_mask.png,masks/scene_000001_frame_000001_goal_37_mask.png | "34,37" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the green whisk to the position of the cooking spoon with green heads and light wooden handles? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from"... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_37_mask.png,masks/scene_000001_frame_000001_goal_10_mask.png | "37,10" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the kitchen spatulas to the location of the salad serving utensils? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "path:... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the light green whisk with a light green handle to the location of the green colander? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [
"depth_maps/scene_000001_frame_000001_depth.png"
] | masks/scene_000001_frame_000001_target_37_mask.png,masks/scene_000001_frame_000001_goal_34_mask.png | "37,34" |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the pair of salad serving utensils to the location of the collapsible silicone colander? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt"... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the pair of salad serving utensils to the location of the set of whisks? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the pair of salad serving utensils to the location of the two pairs of kitchen spatulas? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt"... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the pair of salad serving utensils to the location of the whisk? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "path: [[... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the pairs of kitchen spatulas to the location of the whisk? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "path: [[1022,... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
[
{
"from": "user",
"value": "<image>\nWhat is the 2D pixel path to move the set of whisks to the location of the collapsible silicone colander? Your response should be a list of 2D points that show the path from target object to goal object in that order path: []."
},
{
"from": "gpt",
"value": "p... | [
"images/scene_000001_frame_000001.png"
] | trajectory | 2d | [] | null | null |
End of preview. Expand in Data Studio
BOPASK-Train
BOPASK is a large-scale visual-question-answering dataset for robotic spatial understanding, built on top of four BOP-Challenge: HANDAL, HOPE, LineMOD, and YCB-V.
This release contains 32.68 M training QA pairs across 172 K unique RGB images, covering 8 question types.
Contents
| Family | QA pairs | Unique images |
|---|---|---|
| handal | 442,729 | 4,416 |
| hope | 18,323,007 | 82,229 |
| linemod | 13,165,385 | 61,883 |
| ycbv | 749,461 | 23,524 |
| Total | 32,680,582 | 172,052 |
Question-type breakdown (all families combined)
| Question type | Count |
|---|---|
| trajectory | 13,552,164 |
| spatial_reasoning | 8,888,686 |
| depth_relative | 7,256,308 |
| pose | 1,438,641 |
| grasp | 853,401 |
| depth_absolute | 446,658 |
| object_rearrangement | 157,095 |
| camera (extrinsics) | 87,629 |
Layout
bopask-train/
├── handal/
│ ├── bopask-handal-train.jsonl
│ ├── images/ # RGB frames (.png)
│ ├── depth_maps/ # aligned depth (.png, uint16 mm)
│ └── masks/ # per-object binary masks (.png)
├── hope/ (same structure)
├── linemod/ (same structure)
└── ycbv/ (same structure)
All paths inside each jsonl are family-relative:
images/<basename>.pngdepth_maps/<basename>_depth.pngmasks/<basename>_..._mask.png(comma-separated if multiple objects)
Record format (LLaVA-style)
Each line of a *-train.jsonl is a JSON object:
{
"conversations": [
{"from": "user", "value": "<image>\n<question>"},
{"from": "gpt", "value": "<answer>"}
],
"images": ["images/scene_000000_frame_000000.png"],
"depths": ["depth_maps/scene_000000_frame_000000_depth.png"],
"masks": "masks/scene_000000_frame_000000_obj_000018_mask.png",
"question_type": "pose",
"question_subtype": "matrix",
"object_id": 18
}
Field notes
conversations: a user/assistant turn pair. The user prompt starts with the<image>sentinel token used by many VLMs (e.g. LLaVA / Qwen-VL).images,depths: lists of paths relative to the family folder.masks: a single string. If multiple masks are relevant (e.g. pairwisetrajectory,spatial_reasoning,object_rearrangementquestions) they are comma-separated:"masks/...target..._mask.png,masks/...goal..._mask.png". Some rows havemasks: nullwhen the question does not target a specific object (e.g.cameraextrinsics). Masks are optional for most downstream uses.object_id: integer for single-object questions, or a"target,goal"string for pairwise ones. Absent forcameraquestions.question_type: one ofpose,grasp,camera,depth_absolute,depth_relative,spatial_reasoning,trajectory,object_rearrangement.question_subtype: further specifies the answer format (e.g.matrix/quaternion/2dbbox/3dbboxforpose;2d/3dfortrajectory; etc.).
Known caveats
- A very small number of depth / mask files (≈0.004% of rows, mostly in
LineMOD scenes 12 & 39) are absent because the originals were not recoverable.
The JSONLs still reference them so you may want to handle
FileNotFoundErrorgracefully in your loader. masksare not strictly required for most VQA training setups; downstream users who only need RGB + depth + the conversations can safely ignore them.
Quick start
import json
from datasets import load_dataset
ds = load_dataset(
"bhatvineet/bopask-train",
data_files={"handal": "handal/bopask-handal-train.jsonl",
"hope": "hope/bopask-hope-train.jsonl",
"linemod": "linemod/bopask-linemod-train.jsonl",
"ycbv": "ycbv/bopask-ycbv-train.jsonl"},
)
print(ds)
Or streaming one family at a time:
import json
path = "handal/bopask-handal-train.jsonl"
with open(path) as f:
for line in f:
rec = json.loads(line)
# rec["images"][0] is relative to the "handal/" folder
...
Citation
If you use this dataset, please cite the BOPASK paper and the underlying BOP-Challenge object-pose datasets (HANDAL, HOPE, LineMOD, YCB-V).
License
Released under the MIT License for the question-answer annotations. The underlying RGB, depth, and mask assets inherit the license of their source BOP-Challenge datasets.
- Downloads last month
- 13