Random-access neural compression of material textures

K Vaidyanathan, M Salvi, B Wronski… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …

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 …

ExtraNet: real-time extrapolated rendering for low-latency temporal supersampling

J Guo, X Fu, L Lin, H Ma, Y Guo, S Liu… - ACM Transactions on …, 2021 - dl.acm.org
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 …

Temporally stable real-time joint neural denoising and supersampling

MM Thomas, G Liktor, C Peters, S Kim… - Proceedings of the …, 2022 - dl.acm.org
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 …

Binary opacity grids: Capturing fine geometric detail for mesh-based view synthesis

C Reiser, S Garbin, PP Srinivasan, D Verbin… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

Vectorization for fast, analytic, and differentiable visibility

Y Zhou, L Wu, R Ramamoorthi, LQ Yan - ACM Transactions on Graphics …, 2021 - dl.acm.org
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 …

A reduced-precision network for image reconstruction

MM Thomas, K Vaidyanathan, G Liktor… - ACM Transactions on …, 2020 - dl.acm.org
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 …

Effect-based multi-viewer caching for cloud-native rendering

A Weinrauch, W Tatzgern, P Stadlbauer… - ACM Transactions on …, 2023 - dl.acm.org
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 …

Neural shadow mapping

S Datta, D Nowrouzezahrai, C Schied… - ACM SIGGRAPH 2022 …, 2022 - dl.acm.org
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 …

Adaptive Recurrent Frame Prediction with Learnable Motion Vectors

Z Wu, C Zuo, Y Huo, Y Yuan, Y Peng, G Pu… - SIGGRAPH Asia 2023 …, 2023 - dl.acm.org
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 …