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 …
texture data and, consequently, increasing storage and memory demands. To address this …
Efficient neural supersampling on a novel gaming dataset
A Mercier, R Erasmus, Y Savani… - Proceedings of the …, 2023 - openaccess.thecvf.com
Real-time rendering for video games has become increasingly challenging due to the need
for higher resolutions, framerates and photorealism. Supersampling has emerged as an …
for higher resolutions, framerates and photorealism. Supersampling has emerged as an …
ExtraNet: real-time extrapolated rendering for low-latency temporal supersampling
Both the frame rate and the latency are crucial to the performance of realtime rendering
applications such as video games. Spatial supersampling methods, such as the Deep …
applications such as video games. Spatial supersampling methods, such as the Deep …
Temporally stable real-time joint neural denoising and supersampling
Recent advances in ray tracing hardware bring real-time path tracing into reach, and ray
traced soft shadows, glossy reflections, and diffuse global illumination are now common …
traced soft shadows, glossy reflections, and diffuse global illumination are now common …
Binary opacity grids: Capturing fine geometric detail for mesh-based view synthesis
While surface-based view synthesis algorithms are appealing due to their low computational
requirements, they often struggle to reproduce thin structures. In contrast, more expensive …
requirements, they often struggle to reproduce thin structures. In contrast, more expensive …
Vectorization for fast, analytic, and differentiable visibility
In Computer Graphics, the two main approaches to rendering and visibility involve ray
tracing and rasterization. However, a limitation of both approaches is that they essentially …
tracing and rasterization. However, a limitation of both approaches is that they essentially …
A reduced-precision network for image reconstruction
Neural networks are often quantized to use reduced-precision arithmetic, as it greatly
improves their storage and computational costs. This approach is commonly used in image …
improves their storage and computational costs. This approach is commonly used in image …
Effect-based multi-viewer caching for cloud-native rendering
With cloud computing becoming ubiquitous, it appears as virtually everything can be offered
as-a-service. However, real-time rendering in the cloud forms a notable exception, where …
as-a-service. However, real-time rendering in the cloud forms a notable exception, where …
Neural shadow mapping
We present a neural extension of basic shadow mapping for fast, high quality hard and soft
shadows. We compare favorably to fast pre-filtering shadow mapping, all while producing …
shadows. We compare favorably to fast pre-filtering shadow mapping, all while producing …
Adaptive Recurrent Frame Prediction with Learnable Motion Vectors
The utilization of dedicated ray tracing graphics cards has revolutionized the production of
stunning visual effects in real-time rendering. However, the demand for high frame rates and …
stunning visual effects in real-time rendering. However, the demand for high frame rates and …