{"total":13,"items":[{"citing_arxiv_id":"2606.30608","ref_index":20,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image","primary_cat":"cs.CV","submitted_at":"2026-06-29T17:44:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29786","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments","primary_cat":"cs.CV","submitted_at":"2026-06-29T05:05:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.17824","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Human-in-the-Loop Atlas-Based 3D Asset Segmentation for Interactive Content Workflows","primary_cat":"cs.CV","submitted_at":"2026-06-16T11:51:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.12069","ref_index":89,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Tac-DINO: Learning Vision-Tactile Features with Patch Alignment","primary_cat":"cs.CV","submitted_at":"2026-06-10T13:33:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06485","ref_index":61,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","primary_cat":"cs.CV","submitted_at":"2026-06-04T17:59:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05975","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation","primary_cat":"cs.CV","submitted_at":"2026-06-04T10:16:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16065","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-05-15T15:29:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05411","ref_index":71,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Creative Robot Tool Use by Counterfactual Reasoning","primary_cat":"cs.RO","submitted_at":"2026-05-06T20:10:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Robots discover causal tool features through VLM suggestions and physics-based counterfactual perturbations in simulation, then transfer manipulation skills via conditioned keypoint matching.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23629","ref_index":156,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","primary_cat":"cs.GR","submitted_at":"2026-04-26T09:44:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"surfaces while scaling to 4B parameters. The latest systems TripoSG [9] and MeshCraft [147] push toward high-fidelity mesh generation via flow-based DiT architectures. Part-aware geometry organization.Production assets require per-part control for downstream topology and deformation. Two directions have emerged:recovering parts from holistic geometry- SAMPart3D [156] for multi-granularity segmentation, HoloPart [157] for amodal completion, X-Part [158] for controllable decomposition-andgenerating geometry at the part level-PAGENet [159], PartGen [160], PartCrafter [161], and OmniPart [162] for part-wise reconstruction and editing. 4.2 Topology Generation Geometry generation often produces dense triangle soups with irregular connectivity, inconsistent face den-"},{"citing_arxiv_id":"2604.14927","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"STEP-Parts: Geometric Partitioning of Boundary Representations for Large-Scale CAD Processing","primary_cat":"cs.GR","submitted_at":"2026-04-16T12:12:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05070","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation","primary_cat":"cs.AI","submitted_at":"2026-04-06T18:16:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new framework generates part-level animatable 3D Gaussian vehicles from images by adding modules for exclusive part ownership and kinematic joint/axis prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.27309","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MeshTailor: Cutting Seams via Generative Mesh Traversal","primary_cat":"cs.GR","submitted_at":"2026-03-28T15:30:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.00995","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds","primary_cat":"cs.CV","submitted_at":"2025-11-30T17:32:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}