Problem
Research questions and friction points this paper is trying to address.
HDR video
SDR video
video upconversion
dynamic range
legacy video
Generating HDR Video from SDR Video
🤖 AI Summary
This work addresses the lack of high-quality high dynamic range (HDR) upconversion methods for consumer-grade standard dynamic range (SDR) videos by proposing the first HDR synthesis framework based on generative video models. The approach introduces a Multi-Exposure Video Model (MEVM) to predict an exposure-bracketed sequence and integrates it with a learnable Video Merge Model (VMM) to produce temporally coherent HDR videos that preserve highlight and shadow details. The entire pipeline operates in a physically consistent linear SDR domain. To the best of our knowledge, this is the first effort to leverage large-scale generative video models for SDR-to-HDR conversion, significantly outperforming existing methods across quantitative metrics, visual quality, and user studies, and demonstrating robust HDR reconstruction on both real-world footage and classic films. Project page: sdr2hdrvideo.github.io.
📝 Abstract
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 while preserving detail in both shadows and highlights. Extensive experiments, quantitative and qualitative evaluation, and a user study demonstrate that our approach enables robust HDR conversion for in-the-wild examples from casual consumer videos and even iconic films. Finally, our model can support HDR synthesis pipelines built upon existing SDR generative video models. Output HDR videos can be viewed on our supplementary webpage: sdr2hdrvideo.github.io
Innovation
Methods, ideas, or system contributions that make the work stand out.
HDR video synthesis
Multi-Exposure Video Model
Video Merging Model
SDR-to-HDR conversion
generative video models
🔎 Similar Papers
No similar papers found.
