{"paper":{"title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniela Ivanova, John H. Williamson, Melonie de Almeida, Paul Henderson, Tong Shi","submitted_at":"2026-01-02T13:04:47Z","abstract_excerpt":"Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, an"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"024267b2deef697a55d825b93499a445927c43dbc65c677cf09bd9159cf5ec07"},"source":{"id":"2601.00678","kind":"arxiv","version":3},"verdict":{"id":"3a99a645-2cc1-4cb4-81cd-e05d2bc3844d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:16:01.870709Z","strongest_claim":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames.","one_line_summary":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory.","pith_extraction_headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.00678/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":2,"snapshot_sha256":"203fea5536753bc95fa3d789080eabf1b6a2a225a4d6a209c5c3dffd008f6d29"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}