Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizen Blue Coast for clue delivery! CTOnews.com August 23 news, recently, there is a section of Google AI night photography new technology RawNeRF video fire on the domestic Internet, can perfectly reduce the noise of night photos, accurate restoration, and can synthesize several 2D photos into 3D vision, and can adjust the focus.

CTOnews.com found that the paper on the technology was published in November 2021 and also has a home page on Github.io titled NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images.

As the name suggests, the technology can process noisy night-time images with NeRF (Neural Radiation Field) to synthesize noisy Raw images into high dynamic range views.

NeRF is a simple fully connected neural network that uses information from 2D images as training data to restore volumetric 3D scenes.

While the original NeRF uses tone-mapped low dynamic range LDR images as input, Google modified NeRF to train directly on linear raw images, preserving the full dynamic range of the scene, effectively turning RawNeRF into a multi-image noise reducer capable of combining information from tens or hundreds of input images.

In addition to changing the camera angle, RawNeRF can adjust focus, exposure, and tone mapping later, as demonstrated in the video.

CTOnews.com friends should have been amazed by Google Camera's powerful "night vision" function. If RawNeRF can be used for Google Camera, then maybe mobile phones can also take clear night 3D visual images, of course not yet.

Paper: arxiv.org/abs/2111.13679

RawNeRF Introduction Home Page: bmild.github.io/rawnerf/

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.