Zip-NeRF Gets Orders of Magnitude Faster to Train, but Rendering Still Crawls at 3-4 FPS
jonstephens85 · x · 2026-10-31
Zip-NeRF processing is now orders of magnitude faster: developer fhahlbohm reports its quality is still among the best he's seen, with 35-minute training being tolerable — but 3-4 FPS rendering remains far too slow, prompting a call to Jon Barron's team for another 10x. Jon Stephens is considering a Zip-NeRF vs 3DGS comparison video, as 3DGS still dominates on render speed.
Related event: Fully-Fused CUDA Zip-NeRF Trains 7x Faster, Renders 10x Faster(2 posts)→
More from Research
- Dana Moshkovitz to lecture on OpenAI's claimed proof of the Unique Games Conjecture — RishiBommasani · 2026-10-31
- Mitrix Bio says anti-aging therapy already in early trials with 70-92 year olds — acmoytoy · 2026-10-31
- Bandits meet LLMs: combining multi-armed bandits with LLMs for adaptive, efficient AI — burkov · 2026-10-31
- Open-source lidar_slam_ros2 adds multi-session map joining without GPS or initial guess — rsasaki0109 · 2026-10-31
- MOSS-Image character LoRA training on 12GB RTX 3060: 7.1GB VRAM, 54s inference — Mycelia_Bygonepath · 2026-10-31
- Stanford CS312 write-up explains sharpness and the edge of stability in pretraining — stanfordnlp · 2026-10-31