{"paper":{"title":"Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proprioception and multi-contact touch enable metric-scale 3D object reconstruction under severe hand occlusion by constraining surfaces with physical signals.","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Gabriele Mario Caddeo, Lorenzo Natale, Pasquale Marra","submitted_at":"2026-04-10T08:32:51Z","abstract_excerpt":"We propose a multimodal, physically grounded approach for metric-scale amodal object reconstruction and pose estimation under severe hand occlusion. Unlike prior occlusion-aware 3D generation methods that rely only on vision, we leverage physical interaction signals: proprioception provides the posed hand geometry, and multi-contact touch constrains where the object surface must lie, reducing ambiguity in occluded regions. We represent object structure as a pose-aware, camera-aligned signed distance field (SDF) and learn a compact latent space with a Structure-VAE. In this latent space, we tra"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments in simulation show that adding proprioception and touch substantially improves completion under occlusion and yields physically plausible reconstructions at correct real-world scale compared to vision-only baselines; we further validate transfer by deploying the model on a real humanoid robot with an end-effector different from those used during training.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that physics-based objectives and differentiable decoder-guidance during finetuning and inference will reliably reduce hand-object interpenetration and align the surface with contact observations without introducing artifacts or scale errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A conditional diffusion model using proprioception and multi-contact touch produces metric-scale, physically consistent 3D object reconstructions under hand occlusion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Proprioception and multi-contact touch enable metric-scale 3D object reconstruction under severe hand occlusion by constraining surfaces with physical signals.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9860c066413b5cfe217ca493941887a916ef73429803b25506b703f42c8d7c41"},"source":{"id":"2604.09100","kind":"arxiv","version":2},"verdict":{"id":"01a7aaa8-156f-4cae-b97a-5341752d2b14","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:18:25.267076Z","strongest_claim":"Experiments in simulation show that adding proprioception and touch substantially improves completion under occlusion and yields physically plausible reconstructions at correct real-world scale compared to vision-only baselines; we further validate transfer by deploying the model on a real humanoid robot with an end-effector different from those used during training.","one_line_summary":"A conditional diffusion model using proprioception and multi-contact touch produces metric-scale, physically consistent 3D object reconstructions under hand occlusion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that physics-based objectives and differentiable decoder-guidance during finetuning and inference will reliably reduce hand-object interpenetration and align the surface with contact observations without introducing artifacts or scale errors.","pith_extraction_headline":"Proprioception and multi-contact touch enable metric-scale 3D object reconstruction under severe hand occlusion by constraining surfaces with physical signals."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09100/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}