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
Sampart3d: Segment any part in 3d objects
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 13roles
background 1polarities
unclear 1representative citing papers
OP3DSG generates unified part-aware open-vocabulary 3D scene graphs via knowledge-guided detection, 3D fusion, and LLM-refined prior graphs, with a new UniGraph3D benchmark showing SOTA results for robotics tasks.
MeshTailor is a mesh-native generative model that uses ChainingSeams serialization and a dual-stream transformer with pointer layers to trace coherent seams vertex-by-vertex on 3D surfaces.
Tac-DINO constructs a large tactile dataset and Vis-Tac Holographic Matching Benchmark, then proposes Vision-Tactile Patch Alignment (VTPA) methods that outperform non-aligned baselines on local-to-global feature matching.
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.
A framework for robust 3D segmentation in editable Gaussian Splatting that combines SAM-HQ masks with prior-guided multiview-consistent label assignment to 3D Gaussians.
Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.
A new framework generates part-level animatable 3D Gaussian vehicles from images by adding modules for exclusive part ownership and kinematic joint/axis prediction.
A human-in-the-loop pipeline generates usable segmented 2D atlases from diverse 3D geometries by using greedy view selection, SAM 2 interactive segmentation, and UV back-projection, with recurring manual corrections needed for fine structures, cavities, and weak boundaries.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
STEP-Parts produces tessellation-robust geometric part labels from STEP B-Reps by deterministic merging of same-primitive faces, enabling consistent supervision on 180k+ models.
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.
T-FunS3D is a task-driven hierarchical method for open-vocabulary 3D functionality segmentation that constructs an open-vocabulary scene graph and applies vision-language models to achieve comparable accuracy with faster runtime and lower memory on SceneFun3D.
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.
-
OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments
OP3DSG generates unified part-aware open-vocabulary 3D scene graphs via knowledge-guided detection, 3D fusion, and LLM-refined prior graphs, with a new UniGraph3D benchmark showing SOTA results for robotics tasks.
-
MeshTailor: Cutting Seams via Generative Mesh Traversal
MeshTailor is a mesh-native generative model that uses ChainingSeams serialization and a dual-stream transformer with pointer layers to trace coherent seams vertex-by-vertex on 3D surfaces.
-
Tac-DINO: Learning Vision-Tactile Features with Patch Alignment
Tac-DINO constructs a large tactile dataset and Vis-Tac Holographic Matching Benchmark, then proposes Vision-Tactile Patch Alignment (VTPA) methods that outperform non-aligned baselines on local-to-global feature matching.
-
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.
-
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
A framework for robust 3D segmentation in editable Gaussian Splatting that combines SAM-HQ masks with prior-guided multiview-consistent label assignment to 3D Gaussians.
-
Creative Robot Tool Use by Counterfactual Reasoning
Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.
-
Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation
A new framework generates part-level animatable 3D Gaussian vehicles from images by adding modules for exclusive part ownership and kinematic joint/axis prediction.
-
Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows
A human-in-the-loop pipeline generates usable segmented 2D atlases from diverse 3D geometries by using greedy view selection, SAM 2 interactive segmentation, and UV back-projection, with recurring manual corrections needed for fine structures, cavities, and weak boundaries.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing
STEP-Parts produces tessellation-robust geometric part labels from STEP B-Reps by deterministic merging of same-primitive faces, enabling consistent supervision on 180k+ models.
-
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.
-
T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation
T-FunS3D is a task-driven hierarchical method for open-vocabulary 3D functionality segmentation that constructs an open-vocabulary scene graph and applies vision-language models to achieve comparable accuracy with faster runtime and lower memory on SceneFun3D.