Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaptive sampling at target sampling rate

A technology of adaptive sampling and sampling rate, applied in 3D image processing, processor architecture/configuration, image enhancement, etc., can solve problems such as inability to achieve image quality

Pending Publication Date: 2022-05-24
NVIDIA CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The stepped distribution is usually not averaged over time to equal the importance map, and thus may not achieve the desired image quality for a fixed budget

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adaptive sampling at target sampling rate
  • Adaptive sampling at target sampling rate
  • Adaptive sampling at target sampling rate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Systems and methods involving adaptive sampling at a target sampling rate are disclosed. The target sample rate can be determined based on the desired frame rate or image quality. The target sampling rate is applied to the number of pixels per image (or frame) to calculate the total number of samples. In an embodiment, the target sample rate is not an integer and is represented as a floating point number to best correspond to the real-time frame rate. The total number of samples is then distributed over the image in an importance map-based manner and quantized to an integer sampling rate for each pixel. Quantization is performed using random values ​​to produce a distribution that closely matches the distribution of the importance map.

[0027] FIG. 1A shows an importance map 100 and a threshold-based sampling map 105 generated using the prior art. The importance map is usually as large as the image to be rendered and defines the importance or priority value of each ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Image quality may be improved by rendering an image based on an importance map that indicates image regions that would benefit from more samples. The adaptive sampling uses a target sampling rate and an importance map for the image to determine a number of samples for each pixel of the image. The number of samples per pixel needs a non-negative integer value, so per-pixel random values are used to quantify per-pixel sampling rate. The resulting quantized sampling rate provides a sample distribution of a close matching importance map. The random value per pixel may vary over time such that the average value of the distribution matches the importance map more closely.

Description

[0001] claim priority [0002] This application requires U.S. Provisional Application No. entitled "Adaptive Sampling for Ray-Tracing Using a Fixed Budget with Pseudorandom Properties", filed November 2, 2020 .63 / 108,643, and U.S. Provisional Application entitled "Power-of-Two Adaptive Sampling for Rendering Using a Fixed Budget", filed December 18, 2020 The benefit of No. 63 / 127,488, the entire contents of both applications are hereby incorporated by reference. Background technique [0003] Interactive graphics systems offer limited real-time rendering capabilities, forcing a compromise between image quality and frame rate. Rather than simply increasing the number of samples per pixel (spp) per pixel to improve image quality, adaptive sampling distributes a fixed budget of samples across the rendered image, so that allocating more samples to will benefit most from putting more and pixels that assign fewer samples to other pixels. Conventional adaptive sampling techniques ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T1/20G06T1/60G06T5/00G06T7/40G06T15/00
CPCG06T15/005G06T7/40G06T1/20G06T1/60G06T5/70G06T15/06
Inventor T·G·阿肯宁-莫勒J·K·D·尼尔森J·P·安德森
Owner NVIDIA CORP