2021/11/26 by Ben Mildenhall, Peter Hedman, Mildenhall, Ben +8 · 1 voice · 35 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Graphics (cs.GR) #Image Enhancement Techniques #Image and Video Processing (eess.IV) #cs.CV #cs.GR #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2111.13679
Project page: https://bmild.github.io/rawnerf/
arxiv created 2021/11/26 · openalex publication_date 2021/11/26 · arxiv published 2021/11/26 · arxiv updated 2021/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural Radiance Fields (NeRF) is a technique for high quality novel view synthesis from a collection of posed input images. Like most view synthesis methods, NeRF uses tonemapped low dynamic range (LDR) as input; these images have been processed by a lossy camera pipeline that smooths detail, clips highlights, and distorts the simple noise distribution of raw sensor data. We modify NeRF to instead train directly on linear raw images, preserving the scene's full dynamic range. By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks. In addition to changing the camera viewpoint, we can manipulate focus, exposure, and tonemapping after the fact. Although a single raw image appears significantly more noisy than a postprocessed one, we show that NeRF is highly robust to the zero-mean distribution of raw noise. When optimized over many noisy raw inputs (25-200), NeRF produces a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same wide baseline input images. As a result, our method, which we call RawNeRF, can reconstruct scenes from extremely noisy images captured in near-darkness.