Papers › EBSR: Feature Enhanced Burst Super-Resolution With Deformable Alignment

EBSR: Feature Enhanced Burst Super-Resolution With Deformable Alignment

15 Jun 2021Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2021 6archive 2025-07-28

Ziwei Luo, Lei Yu, Xuan Mo, Youwei Li, Lanpeng Jia, Haoqiang Fan, Jian Sun, Shuaicheng Liu

We propose a novel architecture to handle the problem of multi-frame super-resolution (MFSR). The proposed framework is known as Enhanced Burst Super-Resolution (EBSR), which divides the MFSR problem into three parts: alignment, fusion, and reconstruction. We propose a Feature Enhanced Pyramid Cascading and Deformable convolution (FEPCD) module to align multiple low-resolution burst images in the feature level. And then the aligned features are fused by a Cross Non-Local Fusion (CNLF) module. Finally, the SR image is reconstructed by the Long Range Concatenation Network (LRCN). In addition, we build a cascading residual pathway structure (CR) to improve the performance. We conduct several experiments to analyze and demonstrate these modules. Our EBSR model won the champion in the real track and second place in the synthetic track in the NTIRE21 Burst Super-Resolution Challenge.

PaperPDFCode

Code

Algolzw/EBSR officialmentioned in paperpytorch report
algolzw/bsrt pytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Burst Image ReconstructionBurst Image Super-ResolutionMulti-Frame Super-ResolutionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Burst Image Super-Resolution BurstSR EBSR LPIPS 0.024 #8 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR EBSR PSNR 48.23 #8 of 9 Archive leaderboard report
Burst Image Super-Resolution BurstSR EBSR SSIM 0.985 #8 of 9 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst EBSR LPIPS 0.031 #2 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst EBSR PSNR 42.98 #2 of 8 Archive leaderboard report
Burst Image Super-Resolution SyntheticBurst EBSR SSIM 0.972 #2 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNConvolutionDeformable Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections