Papers › Bringing Old Films Back to Life

Bringing Old Films Back to Life

31 Mar 2022CVPR 2022 1arXiv:2203.17276archive 2025-07-28

Ziyu Wan, Bo Zhang, Dongdong Chen, Jing Liao

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based on the hidden knowledge learned from adjacent frames that contain abundant information about the occlusion, which is beneficial to restore challenging artifacts of each frame while ensuring temporal coherency. Moreover, contrasting the representation of the current frame and the hidden knowledge makes it possible to infer the scratch position in an unsupervised manner, and such defect localization generalizes well to real-world degradations. To better resolve mixed degradation and compensate for the flow estimation error during frame alignment, we propose to leverage more expressive transformer blocks for spatial restoration. Experiments on both synthetic dataset and real-world old films demonstrate the significant superiority of the proposed RTN over existing solutions. In addition, the same framework can effectively propagate the color from keyframes to the whole video, ultimately yielding compelling restored films. The implementation and model will be released at https://github.com/raywzy/Bringing-Old-Films-Back-to-Life.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

raywzy/bringing-old-films-back-to-life officialmentioned in paperpytorch 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

Analog Video Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Analog Video Restoration TAPE RTN LPIPS 0.100 #6 of 7 Archive leaderboard report
Analog Video Restoration TAPE RTN PSNR 31.46 #6 of 7 Archive leaderboard report
Analog Video Restoration TAPE RTN SSIM 0.905 #6 of 7 Archive leaderboard report
Analog Video Restoration TAPE RTN VMAF 56.76 #6 of 7 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.

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