ExWarp: Extrapolation and Warping-based Temporal Supersampling for High-frequency Displays
Akanksha Dixit, Yashashwee Chakrabarty, Smruti R. Sarangi

TL;DR
ExWarp uses reinforcement learning to intelligently combine fast warping and slow DNN-based extrapolation methods, achieving 4x frame rate increase with minimal quality loss for high-frequency displays.
Contribution
This paper introduces ExWarp, a novel RL-based framework that adaptively selects between warping and DNN extrapolation to enhance high-frequency display performance.
Findings
Achieves 4x frame rate increase
Maintains high perceived image quality
Reduces latency compared to previous methods
Abstract
High-frequency displays are gaining immense popularity because of their increasing use in video games and virtual reality applications. However, the issue is that the underlying GPUs cannot continuously generate frames at this high rate -- this results in a less smooth and responsive experience. Furthermore, if the frame rate is not synchronized with the refresh rate, the user may experience screen tearing and stuttering. Previous works propose increasing the frame rate to provide a smooth experience on modern displays by predicting new frames based on past or future frames. Interpolation and extrapolation are two widely used algorithms that predict new frames. Interpolation requires waiting for the future frame to make a prediction, which adds additional latency. On the other hand, extrapolation provides a better quality of experience because it relies solely on past frames -- it does…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Video Quality Assessment · CCD and CMOS Imaging Sensors · Thin-Film Transistor Technologies
