{"paper":{"title":"Generating HDR Video from SDR Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large generative video models can synthesize HDR sequences from casual SDR video by first predicting bracketed linear exposures and then merging them.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daisuke Iso, David B. Lindell, Feiran Li, Francesco Banterle, Jiacheng Li, Karanpreet Raja, Kiriakos N. Kutulakos, SaiKiran Tedla, Trevor Canham","submitted_at":"2026-05-14T11:21:10Z","abstract_excerpt":"The high dynamic range (HDR) video ecosystem is approaching maturity, but the problem of upconverting legacy standard dynamic range (SDR) videos persists without a convincing solution. We propose a framework for HDR video synthesis from casual SDR footage by leveraging large-scale generative video models. We introduce a Multi-Exposure Video Model (MEVM) that can predict exposure-bracketed linear SDR video sequences from a single nonlinear SDR video input. We further propose a learnable Video Merging Model (VMM) that merges the predicted exposure-bracketed video into a high-quality HDR sequence"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our approach enables robust HDR conversion for in-the-wild examples from casual consumer videos and even iconic films.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That large-scale generative video models can reliably predict accurate exposure-bracketed linear SDR sequences from a single nonlinear SDR input without introducing artifacts or inconsistencies.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large generative video models can synthesize HDR sequences from casual SDR video by first predicting bracketed linear exposures and then merging them.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0632aa637af76f5deae9e1713fc4f1fbea3ed7a6c4d6f4a3dee67adf36d84091"},"source":{"id":"2605.14703","kind":"arxiv","version":1},"verdict":{"id":"5e5f66c9-39fd-4b76-87a8-626dd3c901e6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:04:39.597770Z","strongest_claim":"our approach enables robust HDR conversion for in-the-wild examples from casual consumer videos and even iconic films.","one_line_summary":"A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That large-scale generative video models can reliably predict accurate exposure-bracketed linear SDR sequences from a single nonlinear SDR input without introducing artifacts or inconsistencies.","pith_extraction_headline":"Large generative video models can synthesize HDR sequences from casual SDR video by first predicting bracketed linear exposures and then merging them."},"references":{"count":300,"sample":[{"doi":"","year":2025,"title":"BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models , author=. 2025 , eprint=","work_id":"c5a22e1c-14b1-4716-b126-ef8e355868ac","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"History-Guided Video Diffusion , author=. 2025 , booktitle=","work_id":"938de7c5-4131-44d1-9aec-b6f9171115cb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Diffusion forcing: Next-token prediction meets full-sequence diffusion , author=. NeurIPS , year=","work_id":"401ca5cf-33f3-4cdb-881e-1127a7cc0e7b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"High dynamic range imaging: Spatially varying pixel exposures , author=. CVPR , year=","work_id":"cec19af7-0b2b-4a26-ade2-559d17b0f5d1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Burst photography for high dynamic range and low-light imaging on mobile cameras , author=. ToG , volume=","work_id":"7626adf3-c6b4-476f-bc24-bf89d822ad29","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":300,"snapshot_sha256":"df46f1e8bed2f95d24a613fa2f70eded973be74ace0ee24ca951e9228e7785f3","internal_anchors":7},"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"}