Skip to main content
GameDev.net gamedev.net

Denoising News

The latest Denoising coverage curated for game developers.

Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising

arXiv cs.GR details a neural denoiser for stochastic Gaussian splatting that keeps the sort-free, blend-free rendering path while cleaning up the added noise. The method targets stable free-camera navigation, and …

Research arXiv cs.GR · 4 days, 19 hours ago
Occlusion-Point Reuse for Ray-Traced Ambient Occlusion and Shadow

A new ray-tracing technique reuses first-hit occlusion points to improve ambient occlusion and soft shadows under tight real-time budgets. By moving reuse into the occluder domain and pairing samples with …

Research arXiv cs.GR · 1 month, 4 weeks ago
Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings

Disney Research Studios has introduced RaNA, a ragged neighborhood attention operator for denoising deep Monte Carlo renders. The method powers RaNAD, the first spatiotemporal neural denoiser for deep images, and …

Research Disney Research Studios · 2 months, 1 week ago
UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising

The introduction of UGD, an unsupervised geometric distance metric, marks a significant advancement in point cloud denoising. This method allows developers to evaluate noisy point clouds without needing ground-truth data, …

Research arXiv cs.GR · 5 months ago
Nonlinear Noise2Noise for Efficient Monte Carlo Denoiser Training

The introduction of a nonlinear approach to Noise2Noise training could significantly enhance Monte Carlo denoiser efficiency. This advancement is particularly relevant for graphics programmers and artists working with HDR images, …

Research arXiv cs.GR · 8 months, 3 weeks ago