Neural Radiance Field Image Refinement through End-to-End Sampling Point Optimization

Kazuhiro Ohta

Satoshi Ono

Neural Radiance Field (NeRF), capable of synthesizing high-quality novel viewpoint images, suffers from issues like artifact occurrence due to its fixed sampling points during rendering. This study proposes a method that optimizes sampling points to reduce artifacts and produce more detailed images.

PDF URL

Featured

Platforms

Adobe’s Project New Depths Brings Radiance Field Editing to the Creative Mainstream

Adobe announced a radiance field editor at Adobe Max.

Michael Rubloff

Nov 6, 2025

Bringing the Harakbut Face to the World — Without Bringing the World to It

I speak to Krisber Aguilar about capturing the sacred Harakbut Face using 3DGS.

Michael Rubloff

Nov 5, 2025

Platforms

Annx Studio and SpotLite Partner to Bring 3DGS Into Fashion

Gaussian Splatting is popping up in fashion.

Michael Rubloff

Nov 3, 2025

Platforms

Spark v0.1.10 Adds SOGSv2 Compression and New Interactive Examples

Spark's newest update brings SOG V2 support.

Michael Rubloff

Nov 1, 2025