Skip to content

GitLab

Unverified Commit b44a4218 authored by Ruilong Li(李瑞龙)'s avatar Ruilong Li(李瑞龙) Committed by GitHub
Browse files

Update CHANGELOG.md

parent a2e36e91
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
CHANGELOG.md
View file @ b44a4218
...@@ -45,7 +45,7 @@ Examples & Benchmarks: ...@@ -45,7 +45,7 @@ Examples & Benchmarks:
## [0.3.5] - 2023-02-23 ## [0.3.5] - 2023-02-23
A stable version that achieves: A stable version that achieves:
- The vanilla Nerf model with 8-layer MLPs can be trained to better quality (+~0.5 PNSR) in 1 hour rather than 1~2 days as in the paper. - The vanilla Nerf model with 8-layer MLPs can be trained to better quality (+0.5 PNSR) in 1 hour rather than days as in the paper.
- The Instant-NGP Nerf model can be trained to equal quality in 4.5 minutes, comparing to the official pure-CUDA implementation. - The Instant-NGP Nerf model can be trained to equal quality in 4.5 minutes, comparing to the official pure-CUDA implementation.
- The D-Nerf model for dynamic objects can also be trained in 1 hour rather than 2 days as in the paper, and with better quality (+~2.5 PSNR). - The D-Nerf model for dynamic objects can also be trained in 1 hour rather than 2 days as in the paper, and with better quality (+~2.5 PSNR).
- Both bounded and unbounded scenes are supported. - Both bounded and unbounded scenes are supported.
...@@ -56,4 +56,4 @@ Links: ...@@ -56,4 +56,4 @@ Links:
Methodologies: Methodologies:
- Single resolution `nerfacc.OccupancyGrid` for synthetic scenes. - Single resolution `nerfacc.OccupancyGrid` for synthetic scenes.
- Contraction methods `nerfacc.ContractionType` for unbounded scenes. - Contraction methods `nerfacc.ContractionType` for unbounded scenes.
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment