arrow
Return

GFFE: G-buffer Free Frame Extrapolation for Low-latency Real-time Rendering

delete2024-11-19
delete0
delete
OA
AI
S
Songyin Wu *
D
Deepak Vembar
A
Anton Sochenov
S
Selvakumar Panneer
S
SungYe Kim
A
Anton Kaplanyan
L
Ling‐Qi Yan
DOI:10.1145/3687923delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Real-time rendering has been embracing ever-demanding effects, such as ray tracing. However, rendering such effects in high resolution and high frame rate remains challenging. Frame extrapolation methods, which do not introduce additional latency as opposed to frame interpolation methods such as DLSS 3 and FSR 3, boost the frame rate by generating future frames based on previous frames. However, it is a more challenging task because of the lack of information in the disocclusion regions and complex future motions, and recent methods also have a high engine integration cost due to requiring G-buffers as input. We propose a G-buffer free frame extrapolation method, GFFE, with a novel heuristic framework and an efficient neural network, to plausibly generate new frames in real time without introducing additional latency. We analyze the motion of dynamic fragments and different types of disocclusions, and design the corresponding modules of the extrapolation block to handle them. After that, a light-weight shading correction network is used to correct shading and improve overall quality. GFFE achieves comparable or better results than previous interpolation and G-buffer dependent extrapolation methods, with more efficient performance and easier integration.
Keywords:
Extrapolation
Low Latency
Warping
G-buffer Free

Journal

ACM Transactions on Graphics cover
ACM Transactions on Graphics
IF:
9.5
Papers:
4.7K
Citations:
3.6W

Organization

U
University of California Santa Barbara
Scholars:
1.2W
Papers: 9.6K
Citations: 3.6W
University of California System cover
University of California System
Scholars:
37.5W
Papers: 33.7W
Citations: 6.6K
I
Intel Corporation
Scholars:
2.7K
Papers: 2.0K
Citations: 6
researcher View more organizations