AI Paper Atlas

Research map / Video / Video segmentation and tracking

COMISR: Compression-Informed Video Super-Resolution

Yinxiao Li, Pengchong Jin, Feng Yang, Ce Liu, Ming-Hsuan Yang, Peyman Milanfar

ICCV 2021 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 50 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add bi-directional recurrent module (ablation)Recur baseline · Vid4 CRF25 (aug CRF15-25)PSNR (Y-channel): 24.23 -> 24.74Improved
add detail-aware flow estimation (ablation)Recur + a · Vid4 CRF25 (aug CRF15-25)PSNR (Y-channel): 24.74 -> 24.92Improved
add Laplacian enhancement module (ablation)Recur + ab · Vid4 CRF25 (aug CRF15-25)PSNR (Y-channel): 24.92 -> 24.97Improved
add bi-directional recurrent module (ablation)Recur baseline · Vid4 CRF25 (no compression aug)PSNR (Y-channel): 23.97 -> 24.24Improved
add compressed images (CRF15-25) in last 20% of training (ablation)COMISR · Vid4 CRF25PSNR (Y-channel): 24.31 -> 24.97Improved
add compression augmentation in training (ablation)COMISR · Vid4 uncompressedPSNR (Y-channel): 27.48 -> 27.31Hurt
apply STDF video denoiser before VSREDVR · Vid4 CRF25PSNR (Y-channel): 24.45 -> 22.56Hurt
apply STDF video denoiser before VSRTecoGan · Vid4 CRF25PSNR (Y-channel): 23.94 -> 22.25Hurt
apply STDF video denoiser before VSRRSDN · Vid4 CRF25PSNR (Y-channel): 24.06 -> 22.19Hurt
compare COMISR with prior VSR on compressed REDS4COMISR vs EDVR · REDS4 CRF25 (RGB)PSNR (Y-channel): 25.98 -> 26.47Improved
compare COMISR with RSDN on uncompressed Vid4COMISR vs RSDN · Vid4 uncompressedPSNR (Y-channel): 27.92 -> 27.31Hurt

Later papers that compared with this method

2 later accepted papers report COMISR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy