articulated object
articulated-objects-interactive-image-gen
Real-World Evaluation Images for Articulated Objects Interaction Generation
This dataset contains the real-world images used in evaluating DragAPart, a conditional image generator that models interaction with articulated objects.
📦 How to Use It?
Each sample consists of:
original_image_XXX.png: The base image showing an articulated object.
arrow_locations_XXX.npy: A NumPy file containing the arrow coordinates for interaction.
The .npy file stores one arrow as:
[x0, y0… See the full description on the dataset page: https://huggingface.co/datasets/rayli/articulated-objects-interactive-image-gen.Articulated-Object-Code
Articulated-Object-Code
3D articulated objects (objects with moving parts — drawers, hinges, wheels, scissors,
robot arms, …) generated from natural-language descriptions by the LAM pipeline
(Language-driven Articulated Mesh Generation): a multi-stage LLM pipeline that writes
geometry code and assembles it into a URDF + meshes robot description.
Each object ships its generated.urdf (links + joints), the part meshes it references,
materials, the generation configs (including the… See the full description on the dataset page: https://huggingface.co/datasets/YipengGao/Articulated-Object-Code.robocasa_for_articulated_objects
RoboCasa365 Pi0.5 bundled release
This is the self-contained data release for the fixed RoboCasa365 Pi0.5
three-arm study: native, ours, and native_plus_ours. It contains the
converted LeRobot assets selected by the frozen study manifests and the
matching full-population normalization statistics.
Layout
The converted asset trees are packaged in deterministic, uncompressed tar
shards under bundles/. Downloaders must verify BUNDLE_INDEX.json and
extract every shard… See the full description on the dataset page: https://huggingface.co/datasets/Josef5838/robocasa_for_articulated_objects.