Real-time

Multi-Layer Reservoir Splatting for Temporal Reuse under Disocclusion

ReSTIR [Bitterli et al. 2020] efficiently reduces path tracing noise by reusing samples spatiotemporally. Recent ReSTIR methods [Liu et al. 2025] improve temporal reuse from prior frame primary hits. But disocclusions still invalidate some pixel …

Taming optimization variance in compact neural shading networks

We present a training algorithm to mitigate optimization instabilities in small neural networks, like those used in real-time neural shading applications. While large, overparameterized models exhibit predictable convergence, smaller architectures …

VideoNeuMat: Neural Material Extraction from Generative Video Models

Creating photorealistic materials for 3D rendering requires exceptional artistic skill. Generative models for materials could help, but are currently limited by the lack of high-quality training data. While recent video generative models effortlessly …

Real-Time Neural Appearance Models

We present a complete system for real-time rendering of scenes with complex appearance previously reserved for offline use. This is achieved with a combination of algorithmic and system level innovations.Our appearance model utilizes learned …

Evaluating and Improving Rendered Visual Experiences

Rendered imagery is presented to us daily. Special effects in movies, video games, scientific visualizations, and marketing catalogs all often rely on images generated through computer graphics. However, with all the possibilities that rendering …

Random-Access Neural Compression of Material Textures

The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed …

Ray-aligned Occupancy Map Array for Fast Approximate Ray Tracing

We present a new software ray tracing solution that efficiently computes visibilities in dynamic scenes. We first introduce a novel scene representation: ray-aligned occupancy map array (ROMA) that is generated by rasterizing the dynamic scene once …

Luminance-Preserving and Temporally Stable Daltonization

We propose a novel, real-time algorithm for recoloring images to improve the experience for a color vision deficient observer. The output is temporally stable and preserves luminance, the most important visual cue. It runs in 0.2 ms per frame on a …

Joint Neural Denoising of Surfaces and Volumes

We combine state-of-the-art techniques into a system for high-quality, interactive rendering of participating media. We leverage unbiased volume path tracing with multiple scattering, temporally stable neural denoising and NanoVDB, a fast, sparse …

Real-Time Path Tracing and Beyond

Real-time graphics is on the cusp of a historic transition to path tracing. With recent advances in hardware ray tracing, systems research, stochastic light sampling, and denoising, we show that complex light transport effects can be path traced in …