End-to-End Adaptive Monte Carlo Denoising and Super-Resolution

08/16/2021
by   Xinyue Wei, et al.
0

The classic Monte Carlo path tracing can achieve high quality rendering at the cost of heavy computation. Recent works make use of deep neural networks to accelerate this process, by improving either low-resolution or fewer-sample rendering with super-resolution or denoising neural networks in post-processing. However, denoising and super-resolution have only been considered separately in previous work. We show in this work that Monte Carlo path tracing can be further accelerated by joint super-resolution and denoising (SRD) in post-processing. This new type of joint filtering allows only a low-resolution and fewer-sample (thus noisy) image to be rendered by path tracing, which is then fed into a deep neural network to produce a high-resolution and clean image. The main contribution of this work is a new end-to-end network architecture, specifically designed for the SRD task. It contains two cascaded stages with shared components. We discover that denoising and super-resolution require very different receptive fields, a key insight that leads to the introduction of deformable convolution into the network design. Extensive experiments show that the proposed method outperforms previous methods and their variants adopted for the SRD task.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

page 9

page 10

research
06/24/2021

Fast Monte Carlo Rendering via Multi-Resolution Sampling

Monte Carlo rendering algorithms are widely used to produce photorealist...
research
09/16/2019

TextSR: Content-Aware Text Super-Resolution Guided by Recognition

Scene text recognition has witnessed rapid development with the advance ...
research
03/25/2021

JDSR-GAN: Constructing A Joint and Collaborative Learning Network for Masked Face Super-Resolution

With the growing importance of preventing the COVID-19 virus, face image...
research
04/25/2020

Deep Photon Mapping

Recently, deep learning-based denoising approaches have led to dramatic ...
research
08/18/2019

Image Formation Model Guided Deep Image Super-Resolution

We present a simple and effective image super-resolution algorithm that ...
research
12/29/2021

Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge

Autonomous systems are highly vulnerable to a variety of adversarial att...
research
03/30/2021

Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool

Monte Carlo path tracer renders noisy image sequences at low sampling co...

Please sign up or login with your details

Forgot password? Click here to reset