Training

Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields

First page

Paper summary

Combines mip-NeRF 360 with grid-based models for 22x faster training.

Ask this paper

Key points

Anti-aliasing for grids: Brings mip-NeRF's anti-aliasing technique to fast grid-based NeRF architectures, combining quality and speed.

22x training speedup: Trains 22x faster than mip-NeRF 360 while achieving comparable or better quality.

Best of both worlds: Overcomes the historical tradeoff between slow-but-accurate MLP NeRFs and fast-but-aliased grid NeRFs.

3D reconstruction: A practical improvement that made high-quality NeRFs much more accessible to production use cases.

Every Monday