{"paper":{"title":"Hand in Silhouette: Synthetic-to-Real Multi-View Hand Reconstruction via Binary Masks","arxiv_id":"2611.16339","primary_cat":"cs.CV","submitted_at":"2026-11-12T05:59:25+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.94,"id":"s0","own":false,"role":"background","text":"Calibrated multi-view hand reconstruction has advanced rapidly, yet the effectiveness of existing methods depends strongly on real captured data, which is costly to acquire, limited in hand-geometry diversity, and often affected by imperfect annotations.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.06,"method":0.0,"result":0.0,"background":0.94,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.53,"id":"s1","own":false,"role":"background","text":"Synthetic data offers a scalable alternative with accurate supervision, but a substantial synthetic-to-real appearance gap hinders its use.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.46,"method":0.0,"result":0.0,"background":0.53,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.96,"id":"s2","own":true,"role":"contribution","text":"To address this, we introduce Hand in Silhouette (SilHand), a calibrated multi-view hand reconstruction framework that operates on binary hand masks, obtainable at low cost either automatically or manually, to reduce the synthetic-to-real observation gap.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.88,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.04,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.96,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"method","text":"Rather than relying on RGB features for 3D lifting, SilHand projects metric 3D hypotheses into each view to query and fuse mask-ray evidence for hand reconstruction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.85,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.91,"id":"s4","own":true,"role":"method","text":"This mask-centric formulation enables training on a large-scale synthetic dataset comprising 46.8k grasping poses and 60k free-hand samples, providing broad coverage of hand geometry while directly transferring to real captured hand geometry.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.91,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.08,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"Across five real-world benchmarks, SilHand improves relative reconstruction accuracy from 49.2% to 63.4% using masks rendered from reference hands.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.22,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.55,"id":"s6","own":true,"role":"interpretation","text":"Moreover, reconstruction accuracy improves consistently as the synthetic training set grows, indicating that broader geometric coverage translates into better real-world performance.","hedge":{"p":0.59,"label":"hedged_possibility"},"own_p":0.93,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.15,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.45,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.55}},{"i":7,"p":0.86,"id":"s7","own":false,"role":"interpretation","text":"While achieving such diversity is difficult with real captured data, it becomes practical under our mask-centric formulation.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.45,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.02,"method":0.02,"result":0.02,"background":0.03,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.86}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Finally, SilHand remains robust under mask corruption, with reconstruction error increasing by at most 1.63 mm.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"interpretation","text":"Together, these results support binary masks as an effective interface for learning hand reconstruction from synthetic geometry.","hedge":{"p":0.69,"label":"asserted"},"own_p":0.68,"main_claim_p":0.89,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"Together, these results support binary masks as an effective interface for learning hand reconstruction from synthetic geometry.","location":"abstract s9","hedge_strength":{"p":0.69,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7635,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.4,"human_participants":0.17,"controlled_comparison":0.68,"randomized_assignment":0.01,"states_quantitative_result":0.99,"compares_with_prior_results":0.89,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.96,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.96,"simulation_or_computation":0.04}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.99,"text":"To address this, we introduce Hand in Silhouette (SilHand), a calibrated multi-view hand reconstruction framework that operates on binary hand masks, obtainable at low cost either automatically or manually, to reduce the synthetic-to-real observation gap.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}