Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 5835-5844Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00580
Keywords
-
Funding
- NSF Graduate Fellowship
Ask authors/readers for more resources
Mip-NeRF is an extension of NeRF that reduces aliasing artifacts, improves fine detail representation, and is more efficient in speed and size compared to NeRF.
The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different resolutions. The straightforward solution of supersampling by rendering with multiple rays per pixel is impractical for NeRF, because rendering each ray requires querying a multilayer perceptron hundreds of times. Our solution, which we call mip-NeRF (a la mipmap), extends NeRF to represent the scene at a continuously-valued scale. By efficiently rendering anti-aliased conical frustums instead of rays, mip-NeRF reduces objectionable aliasing artifacts and significantly improves NeRF's ability to represent fine details, while also being 7% faster than NeRF and half the size. Compared to NeRF, mip-NeRF reduces average error rates by 17% on the dataset presented with NeRF and by 60% on a challenging multiscale variant of that dataset that we present. Mip-NeRF is also able to match the accuracy of a brute-force supersampled NeRF on our multiscale dataset while being 22x faster.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available