- Number
- 10096088
- Published
- 2018-10-09
- Filed
- 2016-09-28
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Bitterli; Benedikt Martin; Novák; Jan; Rousselle; Fabrice Pierre Armand
- CPC
- G06T5/20; G06T5/70
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Image-space denoising regression (grant dup).
Abstract
The disclosure provides an approach for denoising (also referred to as “filtering”) rendered images. In one embodiment, a denoising application takes as input rendered images and feature buffers that encode image information such as surface positions, surface depths, surface normals, surface albedos, and distances to the camera. For each pixel in a received image, the denoising application performs a first-order regression in a predefined neighborhood of the pixel to find a linear combination of pixel features that fits pixel colors in the predefined neighborhood. In such a first-order regression, the local regression weight of each pixel in the neighborhood may be determined using a metric which computes distances based on color values in patches around pixels being compared. In another embodiment, collaborative filtering may be performed in which filtered output from the first-order regression in each neighborhood is averaged with filtered output from overlapping neighborhoods to obtain a final output.
Background
BACKGROUNDField(1) Embodiments presented herein relate to the field of computer image rendering and, in particular, to a robust regression technique for denoising rendered images.Description of the Related Art(2) In Monte Carlo (MC) rendering, pixels are sampled by shooting view rays through the pixels into a virtual scene, with the output color of each pixel being determined based on interactions of associated view rays with objects (or lack of such interactions) in the scene. MC rendering techniques have proven to be effective at rendering realistic images of virtual scenes. However, images rendering using MC rendering techniques are inherently noisy. Such noise can be reduced by running the renderer longer, but the level of noise decreases only with the square root of samples used in the rendering. As a result, the computational cost of generating perceptually noise-free images can be prohibitively high for many applications such as movie production.SUMMARY(3) One embodiment provides a computer-implemented method for denoising a rendered image. The method generally includes receiving the rendered image and a set of features associated with the image. The method further includes, for each of a plurality of pixels in the image, performing a regression in a predefined neighborhood of the pixel to find a combination of pixel features that fits pixel colors in the predefined neighborhood. In the regression, a local regression weight of each of the pixels in the predefined neigh
Claims
1. A computer-implemented method for denoising a rendered image, comprising: receiving the rendered image and a set of features associated with the rendered image; for each pixel of a plurality of pixels in the rendered image, performing a regression in a predefined neighborhood of the pixel to find a combination of pixel features that fits pixel colors in the predefined neighborhood, wherein, in the regression, a respective local regression weight associated with each pixel in the predefined neighborhood is determined based, at least in part, on a distance metric which computes distances based, at least in part, on color values in patches around pixels being compared; and determining a respective output color value for each pixel of a plurality of pixels in a denoised image corresponding to a respective one of the plurality of pixels in the rendered image based, at least in part, on the fittings produced by a plurality of the regressions.
10. A non-transitory computer-readable storage medium storing instructions, which when executed by a computer system, perform operations for denoising a rendered image, the operations comprising: receiving the rendered image and a set of features associated with the rendered image; for each pixel of a plurality of pixels in the rendered image, performing a regression in a predefined neighborhood of the pixel to find a combination of pixel features that fits pixel colors in the predefined neighborhood, wherein, in the regression, a respective local regression weight associated with each pixel in the predefined neighborhood is determined based, at least in part, on a distance metric which computes distances based, at least in part, on color values in patches around pixels being compared; and determining a respective output color value for each pixel of a plurality of pixels in a denoised image corresponding to a respective one of the plurality of pixels in the rendered image based, at least in part, on the fittings produced by a plurality of the regressions.
19. A system, comprising: a processor; and a memory, wherein the memory includes an application program configured to perform operations for denoising a rendered image, the operations comprising: receiving the rendered image and a set of features associated with the rendered image, for each pixel of a plurality of pixels in the rendered image, performing a regression in a predefined neighborhood of the pixel to find a combination of pixel features that fits pixel colors in the predefined neighborhood, wherein, in the regression, a respective local regression weight associated with each pixel in the predefined neighborhood is determined based, at least in part, on a distance metric which computes distances based, at least in part, on color values in patches around pixels being compared, and determining a respective output color value for each pixel of a plurality of pixels in a denoised image corresponding to a respective one of the plurality of pixels in the rendered image based, at least in part, on the fittings produced by a plurality of the regressions.