{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KJNRUBKFXX56LWFYRYJ4EQYDDS","short_pith_number":"pith:KJNRUBKF","canonical_record":{"source":{"id":"2409.02048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T16:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"83e38ef5685bb61b6e57c9402e6d283b017c9581fee66dba557ce9312fb7226a","abstract_canon_sha256":"fc7d6ae24033f2f6c053445b0028e75a90129631213a64402d6eb62739e9f8d3"},"schema_version":"1.0"},"canonical_sha256":"525b1a0545bdfbe5d8b88e13c243031c9e0458d3560785d3a84bcbc58fed596c","source":{"kind":"arxiv","id":"2409.02048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02048","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02048v1","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02048","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"pith_short_12","alias_value":"KJNRUBKFXX56","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJNRUBKFXX56LWFY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJNRUBKF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KJNRUBKFXX56LWFYRYJ4EQYDDS","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T16:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"83e38ef5685bb61b6e57c9402e6d283b017c9581fee66dba557ce9312fb7226a","abstract_canon_sha256":"fc7d6ae24033f2f6c053445b0028e75a90129631213a64402d6eb62739e9f8d3"},"schema_version":"1.0"},"canonical_sha256":"525b1a0545bdfbe5d8b88e13c243031c9e0458d3560785d3a84bcbc58fed596c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:56:11.849441Z","signature_b64":"gFEvJoKhlgROsLNADJSKgRDZ94qczPfEGuif5SAnFA1TBptvv0yMkcOBlk45Uiti4PjLp9J7xXI045aP4Hz5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"525b1a0545bdfbe5d8b88e13c243031c9e0458d3560785d3a84bcbc58fed596c","last_reissued_at":"2026-05-18T03:56:11.848893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:56:11.848893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02048","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:56:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2rpW3BvC5nMPx3Q81CwX2uyfMBqtqsEgs6JQu6cD+70bNyQsBFECPNWWHulWAJIytHphN0oeHP5e38RQ08DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:38:20.405473Z"},"content_sha256":"c56df36fd7a75cdb0f2b5cb5c1734498d9ae810dc22699a38be5d21d65c325a7","schema_version":"1.0","event_id":"sha256:c56df36fd7a75cdb0f2b5cb5c1734498d9ae810dc22699a38be5d21d65c325a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KJNRUBKFXX56LWFYRYJ4EQYDDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinbo Xing, Li Yuan, Tien-Tsin Wong, Wangbo Yu, Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Ying Shan, Yonghong Tian, Zhipeng Huang","submitted_at":"2024-09-03T16:53:19Z","abstract_excerpt":"Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \\textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images with the prior of video diffusion model. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control. To further enlarge the generation range o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a pre-trained video diffusion model can be reliably steered by coarse point clouds and planned camera trajectories without accumulating geometric drift or view-inconsistency across the iterative synthesis loop.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ViewCrafter tames video diffusion models with point-based 3D guidance and iterative trajectory planning to produce high-fidelity novel views from single or sparse images.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f946154e3b8fd75c03894711ba53b05e093c5a2a365b2b7dc7fa32ea249e0dc2"},"source":{"id":"2409.02048","kind":"arxiv","version":1},"verdict":{"id":"a3488ce9-5b4c-46d5-acb2-04a351fb29e6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:55:10.394119Z","strongest_claim":"Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.","one_line_summary":"ViewCrafter tames video diffusion models with point-based 3D guidance and iterative trajectory planning to produce high-fidelity novel views from single or sparse images.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a pre-trained video diffusion model can be reliably steered by coarse point clouds and planned camera trajectories without accumulating geometric drift or view-inconsistency across the iterative synthesis loop.","pith_extraction_headline":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images."},"references":{"count":79,"sample":[{"doi":"","year":2020,"title":"Nerf: Representing scenes as neural radiance fields for view synthesis","work_id":"a5c56e17-09a0-442d-9bbe-e00f14649493","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"3d gaus- sian splatting for real-time radiance field rendering","work_id":"929feeff-4566-4c44-9f00-4437da4c2116","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Synsin: End-to- end view synthesis from a single image","work_id":"aee8ef3a-c51b-4421-88a4-f92407c79672","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Geometry-free view syn- thesis: Transformers and no 3d priors","work_id":"c420b572-0999-40eb-9f35-ca488dd4e313","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Pixelsynth: Generating a 3d-consistent experience from a single image","work_id":"a9f5c957-a190-4700-8887-02c739842b15","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":79,"snapshot_sha256":"3c8d1150af188bb1366e3a29713c6323ee458ec3cc5eee7f5db334fc11e0d1d2","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0738044f8660da61f168ba445718ca4f660c1e8cf3aa2070da2006ee1fb3eb70"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"a3488ce9-5b4c-46d5-acb2-04a351fb29e6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:56:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Rzt/uCTjfr2k1QOZqiMHHNcNJ9FMBFUO808Vx6c9BTuDn5Rkm6yZ05xjH/R3Em2+8TPvbb+9D768WldsV75Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:38:20.406305Z"},"content_sha256":"368c184c05b0dcb3d788d62e8a8eee21d75dcb92a4d42c2335936ac012667356","schema_version":"1.0","event_id":"sha256:368c184c05b0dcb3d788d62e8a8eee21d75dcb92a4d42c2335936ac012667356"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/bundle.json","state_url":"https://pith.science/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T19:38:20Z","links":{"resolver":"https://pith.science/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS","bundle":"https://pith.science/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/bundle.json","state":"https://pith.science/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJNRUBKFXX56LWFYRYJ4EQYDDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJNRUBKFXX56LWFYRYJ4EQYDDS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fc7d6ae24033f2f6c053445b0028e75a90129631213a64402d6eb62739e9f8d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T16:53:19Z","title_canon_sha256":"83e38ef5685bb61b6e57c9402e6d283b017c9581fee66dba557ce9312fb7226a"},"schema_version":"1.0","source":{"id":"2409.02048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02048","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02048v1","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02048","created_at":"2026-05-18T03:56:11Z"},{"alias_kind":"pith_short_12","alias_value":"KJNRUBKFXX56","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KJNRUBKFXX56LWFY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KJNRUBKF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:368c184c05b0dcb3d788d62e8a8eee21d75dcb92a4d42c2335936ac012667356","target":"graph","created_at":"2026-05-18T03:56:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a pre-trained video diffusion model can be reliably steered by coarse point clouds and planned camera trajectories without accumulating geometric drift or view-inconsistency across the iterative synthesis loop."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ViewCrafter tames video diffusion models with point-based 3D guidance and iterative trajectory planning to produce high-fidelity novel views from single or sparse images."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images."}],"snapshot_sha256":"f946154e3b8fd75c03894711ba53b05e093c5a2a365b2b7dc7fa32ea249e0dc2"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0738044f8660da61f168ba445718ca4f660c1e8cf3aa2070da2006ee1fb3eb70"},"paper":{"abstract_excerpt":"Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \\textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images with the prior of video diffusion model. Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control. To further enlarge the generation range o","authors_text":"Jinbo Xing, Li Yuan, Tien-Tsin Wong, Wangbo Yu, Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Ying Shan, Yonghong Tian, Zhipeng Huang","cross_cats":[],"headline":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T16:53:19Z","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"},"references":{"count":79,"internal_anchors":7,"resolved_work":79,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Nerf: Representing scenes as neural radiance fields for view synthesis","work_id":"a5c56e17-09a0-442d-9bbe-e00f14649493","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"3d gaus- sian splatting for real-time radiance field rendering","work_id":"929feeff-4566-4c44-9f00-4437da4c2116","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Synsin: End-to- end view synthesis from a single image","work_id":"aee8ef3a-c51b-4421-88a4-f92407c79672","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Geometry-free view syn- thesis: Transformers and no 3d priors","work_id":"c420b572-0999-40eb-9f35-ca488dd4e313","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Pixelsynth: Generating a 3d-consistent experience from a single image","work_id":"a9f5c957-a190-4700-8887-02c739842b15","year":2021}],"snapshot_sha256":"3c8d1150af188bb1366e3a29713c6323ee458ec3cc5eee7f5db334fc11e0d1d2"},"source":{"id":"2409.02048","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T22:55:10.394119Z","id":"a3488ce9-5b4c-46d5-acb2-04a351fb29e6","model_set":{"reader":"grok-4.3"},"one_line_summary":"ViewCrafter tames video diffusion models with point-based 3D guidance and iterative trajectory planning to produce high-fidelity novel views from single or sparse images.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ViewCrafter steers a pre-trained video diffusion model with coarse point clouds and planned trajectories to synthesize consistent high-fidelity novel views from single or sparse images.","strongest_claim":"Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames with precise camera pose control.","weakest_assumption":"That a pre-trained video diffusion model can be reliably steered by coarse point clouds and planned camera trajectories without accumulating geometric drift or view-inconsistency across the iterative synthesis loop."}},"verdict_id":"a3488ce9-5b4c-46d5-acb2-04a351fb29e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c56df36fd7a75cdb0f2b5cb5c1734498d9ae810dc22699a38be5d21d65c325a7","target":"record","created_at":"2026-05-18T03:56:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fc7d6ae24033f2f6c053445b0028e75a90129631213a64402d6eb62739e9f8d3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T16:53:19Z","title_canon_sha256":"83e38ef5685bb61b6e57c9402e6d283b017c9581fee66dba557ce9312fb7226a"},"schema_version":"1.0","source":{"id":"2409.02048","kind":"arxiv","version":1}},"canonical_sha256":"525b1a0545bdfbe5d8b88e13c243031c9e0458d3560785d3a84bcbc58fed596c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"525b1a0545bdfbe5d8b88e13c243031c9e0458d3560785d3a84bcbc58fed596c","first_computed_at":"2026-05-18T03:56:11.848893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:56:11.848893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFEvJoKhlgROsLNADJSKgRDZ94qczPfEGuif5SAnFA1TBptvv0yMkcOBlk45Uiti4PjLp9J7xXI045aP4Hz5DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:56:11.849441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c56df36fd7a75cdb0f2b5cb5c1734498d9ae810dc22699a38be5d21d65c325a7","sha256:368c184c05b0dcb3d788d62e8a8eee21d75dcb92a4d42c2335936ac012667356"],"state_sha256":"c8e0188d1f231df9370f1cda1aacdeca96fed0a43b9450a73e3ea2bf03bb2139"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eat10lXFihPpoZjlmSuIHjqUKfESNbMIfs3cmMNAMJWZa8XhHUMFsw6z/+lo5TwldlfZXcFuF9HX3ceJOpp1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T19:38:20.409732Z","bundle_sha256":"3856fc6869508ec0ffdd3950dd811ade43eb2217184eead1b1c0b28b7f3f33e0"}}