We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images.

May 3, 2021 · We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images.

This work proposes a two-stage model that first processes an input image with a small set of specialized denoisers, and then passes the resulting ...

We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images. Instead of taking a conventional ...

We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images.

This application claims priority benefit of the United States Provisional Patent Application titled, “ROBUST IMAGE DENOISING USING KERNEL PREDICTING NETWORKS,” ...

We present a new method for designing high quality denoisers that are robust to varying noise characteristics of input images.

Inference Time vs. Denoising Quality. We investigated how various modifications to the KPCN general- izer with the goal of reducing inference and training ...

Regression-based algorithms have shown to be good at denoising Monte Carlo (MC) renderings by leveraging its inexpensive by-products (e.g., feature buffers) ...

We present a technique for jointly denoising bursts of im- ages taken from a handheld camera. In particular, we pro- pose a convolutional neural network ...