jonbarron.info/zipnerf
Preview meta tags from the jonbarron.info website.
Linked Hostnames
10- 2 links todorverbin.github.io
- 2 links togithub.com
- 1 link toarxiv.org
- 1 link tobmild.github.io
- 1 link tojonbarron.info
- 1 link tomgharbi.com
- 1 link tophogzone.com
- 1 link topratulsrinivasan.github.io
Thumbnail
Search Engine Appearance
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content. Anti-aliasing has previously been addressed by mip-NeRF 360, which reasons about sub-volumes along a cone rather than points along a ray, but this approach is not natively compatible with current grid-based techniques. We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8%-77% lower than either prior technique, and that trains 24x faster than mip-NeRF 360.
Bing
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content. Anti-aliasing has previously been addressed by mip-NeRF 360, which reasons about sub-volumes along a cone rather than points along a ray, but this approach is not natively compatible with current grid-based techniques. We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8%-77% lower than either prior technique, and that trains 24x faster than mip-NeRF 360.
DuckDuckGo
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content. Anti-aliasing has previously been addressed by mip-NeRF 360, which reasons about sub-volumes along a cone rather than points along a ray, but this approach is not natively compatible with current grid-based techniques. We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8%-77% lower than either prior technique, and that trains 24x faster than mip-NeRF 360.
General Meta Tags
5- titleZip-NeRF
- charsetUTF-8
- x-ua-compatibleie=edge
- description
- viewportwidth=device-width, initial-scale=1
Open Graph Meta Tags
8- og:imagehttps://jonbarron.info/zipnerf/img/nottingham.jpg
- og:image:typeimage/png
- og:image:width1296
- og:image:height840
- og:typewebsite
Twitter Meta Tags
4- twitter:cardsummary_large_image
- twitter:titleZip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
- twitter:descriptionNeural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density. However, these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content. Anti-aliasing has previously been addressed by mip-NeRF 360, which reasons about sub-volumes along a cone rather than points along a ray, but this approach is not natively compatible with current grid-based techniques. We show how ideas from rendering and signal processing can be used to construct a technique that combines mip-NeRF 360 and grid-based models such as Instant NGP to yield error rates that are 8%-77% lower than either prior technique, and that trains 24x faster than mip-NeRF 360.
- twitter:imagehttps://jonbarron.info/zipnerf/img/teaser.jpg
Link Tags
6- icondata:image/svg+xml,<svg xmlns=%22http://www.w3.org/2000/svg%22 viewBox=%220 0 100 100%22><text y=%22.9em%22 font-size=%2290%22>⚡</text></svg>
- stylesheethttps://maxcdn.bootstrapcdn.com/bootstrap/3.3.5/css/bootstrap.min.css
- stylesheethttps://maxcdn.bootstrapcdn.com/font-awesome/4.4.0/css/font-awesome.min.css
- stylesheethttps://cdnjs.cloudflare.com/ajax/libs/codemirror/5.8.0/codemirror.min.css
- stylesheetcss/app.css
Links
12- http://bmild.github.io
- http://dorverbin.github.io
- http://mgharbi.com
- https://arxiv.org/abs/2304.06706
- https://dorverbin.github.io/refnerf