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

XGRIDS Unveils the Lixel L3 Scanner

XGRIDS unveiled the Lixel L3 at INTERGEO 2026, a spatial scanner producing a true-color point cloud, a mesh, and a 3DGS model from a single capture pass.

Michael Rubloff

Sep 15, 2026

Platforms

GeoLibre v3.0.0 Renders Gaussian Splat Tilesets Natively on a Cesium Globe

GeoLibre v3.0.0 renders Gaussian splat tilesets on a Cesium globe through KHR_gaussian_splatting, and adds native I3S scene layers and COPC point clouds.

Michael Rubloff

Sep 15, 2026

Platforms

OfflineTools Runs COLMAP in the Browser, Beats Native SIFT

OfflineTools has released a free browser build of COLMAP that runs fully locally in WebAssembly and reports faster SIFT extraction than the stock native binary.

Michael Rubloff

Sep 15, 2026

Platforms

Arcturus Vision Opens Orders for a $149 Steam Frame Passthrough Camera

Arcturus Vision has opened orders for a $149 5K HDR passthrough camera for Steam Frame, and listed Gaussian XR, a free splat viewer planned for September 2026.

Michael Rubloff

Sep 15, 2026