Google’s NeRF AI just got upgraded with RawNeRF, which can output images in linear HDR color space, so its renderings can be retouched similar to any raw photograph. This enables you to adjust the exposure by scaling the linear image values before applying HDRNet to produce a tonemapped low dynamic range output, effectively denoising a hazy image.
RAW Neural Radiance Fields (RAWNeRF) also enables you to use the linear colors to render synthetic defocus effects with correctly saturated “bokeh” highlights. Most importantly, when you optimize an image over many noisy raw inputs (25-200), NeRF generates a scene representation so accurate that its rendered novel views outperform dedicated single and multi-image deep raw denoisers run on the same exact wide baseline input images. Fortunately, NeRF won’t be creating its own secret language that nobody can understand like Dall-E2.
- Powerful Productivity: AMD Ryzen 3 3350U delivers desktop-class performance and amazing battery life in a slim notebook. With Precision Boost, get up...
- Maximized Visuals: See even more on the stunning 15.6" Full HD display with 82.58% screen-to-body, 16:9 aspect ratio and narrow bezels
- Backlit Keyboard and Fingerprint Reader: Biometric fingerprint reader and Windows Hello sign-in options help keep your Acer PC secure
Training directly on raw data effectively turns RawNeRF into a multi-image denoiser capable of combining information from tens or hundreds of input images. This robustness to noise means that we can use RawNeRF to reconstruct scenes captured in the dark,” said the researchers.
