State of the Art on Deep Learning-enhanced Rendering Methods
Photorealistic rendering of the virtual world is an important and classic problem in the field of
computer graphics. With the development of GPU hardware and continuous research on …
computer graphics. With the development of GPU hardware and continuous research on …
Frame interpolation transformer and uncertainty guidance
Video frame interpolation has seen important progress in recent years, thanks to
developments in several directions. Some works leverage better optical flow methods with …
developments in several directions. Some works leverage better optical flow methods with …
Inovis: Instant novel-view synthesis
Novel-view synthesis is an ill-posed problem in that it requires inference of previously
unseen information. Recently, reviving the traditional field of image-based rendering, neural …
unseen information. Recently, reviving the traditional field of image-based rendering, neural …
Kernel-Based Frame Interpolation for Spatio-Temporally Adaptive Rendering
Recently, there has been exciting progress in frame interpolation for rendered content. In
this offline rendering setting, additional inputs, such as albedo and depth, can be extracted …
this offline rendering setting, additional inputs, such as albedo and depth, can be extracted …
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 …
Mnss: Neural supersampling framework for real-time rendering on mobile devices
Although neural supersampling has achieved great success in various applications for
improving image quality, it is still difficult to apply it to a wide range of real-time rendering …
improving image quality, it is still difficult to apply it to a wide range of real-time rendering …
Efficient light probes for real-time global illumination
J Guo, Z Zong, Y Song, X Fu, C Tao, Y Guo… - ACM Transactions on …, 2022 - dl.acm.org
Reproducing physically-based global illumination (GI) effects has been a long-standing
demand for many real-time graphical applications. In pursuit of this goal, many recent …
demand for many real-time graphical applications. In pursuit of this goal, many recent …
Interactive neural cascade denoising for 1-spp Monte Carlo images
Y Chen, Y Lu, X Zhang, N Xie - The Visual Computer, 2023 - Springer
Monte Carlo (MC) path tracing is known for its high fidelity and heavy computational cost.
With the development of neural networks, the kernel-based post-processing method has …
With the development of neural networks, the kernel-based post-processing method has …
Neural foveated super‐resolution for real‐time VR rendering
J Ye, X Meng, D Guo, C Shang, H Mao… - … Animation and Virtual …, 2024 - Wiley Online Library
As virtual reality display technologies advance, resolutions and refresh rates continue to
approach human perceptual limits, presenting a challenge for real‐time rendering …
approach human perceptual limits, presenting a challenge for real‐time rendering …
Auxiliary Features‐Guided Super Resolution for Monte Carlo Rendering
This paper investigates super‐resolution to reduce the number of pixels to render and thus
speed up Monte Carlo rendering algorithms. While great progress has been made to super …
speed up Monte Carlo rendering algorithms. While great progress has been made to super …