Paper

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

UEFN 43.00 Adds Experimental Gaussian Splat Import

UEFN 43.00 adds experimental Gaussian splat import from PLY and SPZ files, with native rendering on all UEFN platforms including mobile and Niagara integration.

Michael Rubloff

Nov 3, 2026

Platforms

Unity Gaussian Splatting 2.0.0 Loads PLY and SPZ Directly

Unity Gaussian Splatting 2.0.0 loads PLY and SPZ files directly, adding SPZ 4 support, global sorting and a stochastic render mode while dropping splat editing.

Michael Rubloff

Nov 3, 2026

Platforms

OKO 2026.22 Brings Depth of Field to Gaussian Splats

OKO 2026.22 adds Gaussian splat depth of field to its web client and tint and cull modifier volumes for splats on iOS, and makes WebGPU the web default.

Michael Rubloff

Nov 3, 2026

News

Skyline Brings Splat Analysis to TerraExplorer 8.1

Skyline Software Systems says TerraExplorer 8.1 supports georeferenced Gaussian splats alongside GIS data, with basic measurements and analysis on the splat.

Michael Rubloff

Nov 3, 2026