UnfoldArt uses a two-round structured debate between high-level semantic agents and low-level parameter agents, grounded in generated video, to infer articulation and reconstruct full articulated 3D objects including occluded geometry from text or image inputs.
hub
P3-sam: Native 3d part segmentation
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toys4K in Chamfer and Hausdorff distances.
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.
Pxform provides 102,007 semantic-part 3D editing pairs; PartFlow, a mask-free feedforward editor trained on them, reports the best geometry and appearance editing scores on two benchmarks.
A unified generative pipeline produces cross-simulator, affordance-annotated, task-conditioned 3D worlds that support online robot policy training and real-robot transfer.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
ISAP-3D proposes identity-slot aligned modeling with semantic identity tokens and one-to-one layout prediction to achieve stable part-aware 3D generation.
S2AM3D combines multi-view 2D priors with 3D contrastive learning and a scale-aware decoder to deliver consistent, granularity-controllable part segmentation on point clouds, supported by a new dataset exceeding 100k samples.
citing papers explorer
-
UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
UnfoldArt uses a two-round structured debate between high-level semantic agents and low-level parameter agents, grounded in generated video, to infer articulation and reconstruct full articulated 3D objects including occluded geometry from text or image inputs.
-
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
PolyFlow converts discrete meshes to continuous per-vertex representations using a topology embedder and applies flow matching for parallel artist-style mesh generation that outperforms autoregressive baselines on Toys4K in Chamfer and Hausdorff distances.
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
A single RGB image is converted into a layered, simulation-ready robot scene that supports trajectory replay, synthetic data generation, and meaningful sim-real policy evaluation, plus a 564-scene DROID-Sim companion set.
-
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
An automated real-to-sim pipeline builds digital twins and affordance-preserving cousins from video, yielding sim evaluations that correlate with real robot policy success and zero-shot sim-to-real gains.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding
PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.
-
Feedforward 3D Editing Learns from Semantic-Part Transformation
Pxform provides 102,007 semantic-part 3D editing pairs; PartFlow, a mask-free feedforward editor trained on them, reports the best geometry and appearance editing scores on two benchmarks.
-
EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
A unified generative pipeline produces cross-simulator, affordance-annotated, task-conditioned 3D worlds that support online robot policy training and real-robot transfer.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation
ISAP-3D proposes identity-slot aligned modeling with semantic identity tokens and one-to-one layout prediction to achieve stable part-aware 3D generation.
-
S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds
S2AM3D combines multi-view 2D priors with 3D contrastive learning and a scale-aware decoder to deliver consistent, granularity-controllable part segmentation on point clouds, supported by a new dataset exceeding 100k samples.