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 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.

Project page: https://bmild.github.io/rawnerf/

References in corpus (6)

• HDR image reconstruction from a single exposure using deep CNNs
• NeRF--: Neural Radiance Fields Without Known Camera Parameters
• Noise2Self: Blind Denoising by Self-Supervision
• Depth-supervised NeRF: Fewer Views and Faster Training for Free
• In-Place Scene Labelling and Understanding with Implicit Scene Representation
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo