{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BXGWEQZXBNHSEQ4XVQ7KWT2KAR","short_pith_number":"pith:BXGWEQZX","schema_version":"1.0","canonical_sha256":"0dcd6243370b4f224397ac3eab4f4a044bf9349266699a25d40ce8e9a47b1c2e","source":{"kind":"arxiv","id":"2103.12957","version":1},"attestation_state":"computed","paper":{"title":"Multi-view 3D Reconstruction with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Wang, Rabab Ward, Septimiu Salcudean, Tianyang Shi, Xinrui Cui, Xun Chen, Zhengxia Zou, Z. Jane Wang","submitted_at":"2021-03-24T03:14:49Z","abstract_excerpt":"Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.12957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T03:14:49Z","cross_cats_sorted":[],"title_canon_sha256":"e4f72cb75d5ccbf4f909e9828525fb421c120f129e9ddbb195075b451e951556","abstract_canon_sha256":"5f5fdeed1859fc8d32fd86fcf8d7a64ce935b6b96937cf826da803097563080b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:04.130268Z","signature_b64":"bl85QmygfNQnvjux/uJIMvAGagwiizuLjHM+tmXx2azeiKvNpojgKC20YYfN26bEk+3axI0U6iZ1+k3sXR33AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dcd6243370b4f224397ac3eab4f4a044bf9349266699a25d40ce8e9a47b1c2e","last_reissued_at":"2026-07-05T02:26:04.129915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:04.129915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-view 3D Reconstruction with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Wang, Rabab Ward, Septimiu Salcudean, Tianyang Shi, Xinrui Cui, Xun Chen, Zhengxia Zou, Z. Jane Wang","submitted_at":"2021-03-24T03:14:49Z","abstract_excerpt":"Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are usually investigated separately, and the object relations in different views are rarely explored. In this paper, inspired by the recent great success in self-attention-based Transformer models, we reformulate the multi-view 3D reconstruction as a sequence-to-sequence prediction problem and propose a new framework named 3D Volume Transformer (VolT) for such a task."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12957","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.12957/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.12957","created_at":"2026-07-05T02:26:04.129979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12957v1","created_at":"2026-07-05T02:26:04.129979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12957","created_at":"2026-07-05T02:26:04.129979+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXGWEQZXBNHS","created_at":"2026-07-05T02:26:04.129979+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXGWEQZXBNHSEQ4X","created_at":"2026-07-05T02:26:04.129979+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXGWEQZX","created_at":"2026-07-05T02:26:04.129979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00731","citing_title":"Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR","json":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR.json","graph_json":"https://pith.science/api/pith-number/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/graph.json","events_json":"https://pith.science/api/pith-number/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/events.json","paper":"https://pith.science/paper/BXGWEQZX"},"agent_actions":{"view_html":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR","download_json":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR.json","view_paper":"https://pith.science/paper/BXGWEQZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12957&json=true","fetch_graph":"https://pith.science/api/pith-number/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/graph.json","fetch_events":"https://pith.science/api/pith-number/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/action/storage_attestation","attest_author":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/action/author_attestation","sign_citation":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/action/citation_signature","submit_replication":"https://pith.science/pith/BXGWEQZXBNHSEQ4XVQ7KWT2KAR/action/replication_record"}},"created_at":"2026-07-05T02:26:04.129979+00:00","updated_at":"2026-07-05T02:26:04.129979+00:00"}