Title
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
Abstract
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 zeromean 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.
Year
DOI
Venue
2022
10.1109/CVPR52688.2022.01571
IEEE Conference on Computer Vision and Pattern Recognition
Keywords
DocType
Volume
3D from multi-view and sensors, Computational photography, Low-level vision, Vision + graphics
Conference
2022
Issue
Citations 
PageRank 
1
0
0.34
References 
Authors
0
5
Name
Order
Citations
PageRank
Ben Mildenhall121.37
peter hedman2816.63
Ricardo Martin-Brualla300.34
Srinivasan, P.P.48110.65
Jonathan T. Barron588139.55