High-Quality Supersampling via Mask-reinforced Deep Learning for Real-time Rendering

by   Hongliang Yuan, et al.
Southeast University
Tsinghua University
Tencent QQ

To generate high quality rendering images for real time applications, it is often to trace only a few samples-per-pixel (spp) at a lower resolution and then supersample to the high resolution. Based on the observation that the rendered pixels at a low resolution are typically highly aliased, we present a novel method for neural supersampling based on ray tracing 1/4-spp samples at the high resolution. Our key insight is that the ray-traced samples at the target resolution are accurate and reliable, which makes the supersampling an interpolation problem. We present a mask-reinforced neural network to reconstruct and interpolate high-quality image sequences. First, a novel temporal accumulation network is introduced to compute the correlation between current and previous features to significantly improve their temporal stability. Then a reconstruct network based on a multi-scale U-Net with skip connections is adopted for reconstruction and generation of the desired high-resolution image. Experimental results and comparisons have shown that our proposed method can generate higher quality results of supersampling, without increasing the total number of ray-tracing samples, over current state-of-the-art methods.


page 1

page 3

page 4

page 6

page 7


Massively Parallel Ray Tracing Algorithm Using GPU

Ray tracing is a technique for generating an image by tracing the path o...

Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction

This paper presents an adaptive image sampling algorithm based on Deep L...

Real-Time High-Resolution Background Matting

We introduce a real-time, high-resolution background replacement techniq...

Real-time High-Quality Rendering of Non-Rotating Black Holes

We propose a real-time method to render high-quality images of a non-rot...

Towards understanding feedback from supermassive black holes using convolutional neural networks

Supermassive black holes at centers of clusters of galaxies strongly int...

Image scaling by de la Vallée-Poussin filtered interpolation

We present a new image scaling method both for downscaling and upscaling...

HRINet: Alternative Supervision Network for High-resolution CT image Interpolation

Image interpolation in medical area is of high importance as most 3D bio...

Please sign up or login with your details

Forgot password? Click here to reset