arXiv cs.AI· Hanwool Sul, Chang-Hoon Jeong, Kisung Shin, Bomseok Park, Donghoon Cha, Hansl von Kwon, DoHyung Ku, Byoung-Tak Zhang·· 3 小时前AI 评分27
将视频逆色调映射重构为基于潜在亮度监督的盲后验推断
Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision
AI 导读
一项 arXiv 研究将 SDR 视频(HDR)转换中的逆色调映射（ITM）重构为未知算子下的后验推断问题，指出所有公开的生成式方法在饱和区域亮度系统性偏亮或偏暗，并将此定义为"亮度误差"。
正文 · 原文
Abstract:High-dynamic-range (HDR) displays are now common, but most video content, such as archival footage, broadcast material, and the output of generative video models, exists only in standard dynamic range (SDR). The need is sharpest for generated video, which has no HDR master at all and is graded alongside live-action and visual-effects material finished in HDR. Converting SDR to HDR means undoing a tone-mapping operation that was never recorded, and clipping destroys the radiance wherever it acts, so HDR recovery is a blind inverse problem. Methods built on generative video priors fill clipped regions with plausible structure, but their reconstructions are systematically biased: in every public method we test, saturated content leans too bright or too dark, and the direction of the lean moves with the tone operator behind the input. We call this failure the luminance error, measure both its magnitude and its sign, and make it the focus of this work. Reframing ITM as posterior inference under an unknown operator locates the failure in two places and yields two corrections. A fixed affine functional of the video-diffusion latent reads log-luminance without decoding; on that coordinate an asymmetric loss selects an expectile of the posterior, applied only where clipping leaves luminance unconstrained. We also synthesize training SDR through an explicit family of tone operators, so the model marginalizes over what the observation cannot show. Trained this way, our luminance error stays flatter across operators and smaller on average than any public method, and the full system achieves the best perceptual quality on all three benchmarks.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15146 [cs.CV] |
| (or arXiv:2611.15146v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15146 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hanwool Sul [view email]
[v1]
Wed, 11 Nov 2026 07:36:06 UTC (9,091 KB)
来源：arXiv cs.AI · arxiv.org