NTIRE 2023 Challenge on Stereo Image Super-Resolution: Methods and Results

NTIRE 2023 Challenge on Stereo Image Super-Resolution : Methods and Results

In this paper, we summarize the 2nd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of the challenge is to super-resolve a low-resolution stereo image pair to a high-resolution one with a magnification factor of x4. Compared with single image SR, the major challenge of this challenge lies in how to exploit additional information in another viewpoint and how to maintain stereo consistency in the results. This challenge has 3 tracks, including one track on distortion (e.g., PSNR) and bicubic degradation, one track on perceptual quality (e.g., LPIPS) and bicubic degradation, as well as another track on real degradations. In total, 175, 93, and 103 participants were successfully registered for each track, respectively. In the test phase, 21, 17, and 12 teams successfully submitted results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR.

Luo, ZiweiUppsala universitet,Avdelningen för systemteknik,Artificiell intelligens(Swepub:uu)ziwlu272 (author)
Gustafsson, Fredrik K.Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens(Swepub:uu)fregu482 (author)
Zhao, ZhengUppsala universitet,Avdelningen för systemteknik,Artificiell intelligens(Swepub:uu)zhezh438 (author)
Sjölund, Jens,Biträdande lektor,1987-Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens(Swepub:uu)jensj431 (author)
Schön, Thomas B.,Professor,1977-Uppsala universitet,Avdelningen för systemteknik,Artificiell intelligens(Swepub:uu)thosc112 (author)
Zhang, Wenlong (author)
Uppsala universitetAvdelningen för systemteknik (creator_code:org_t)

In:IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Vancover : Institute of Electrical and Electronics Engineers (IEEE), s. 1346-137297983503024939798350302509

By the author/editor: Wang, Longguang; Luo, Ziwei; Gustafsson, Fred ...; Zhao, Zheng; Sjölund, Jens, B ...; Schön, Thomas B. ...; show more...; Zhang, Wenlong; show less...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Signal Processin ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.