AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Degradation-Robust Spatiotemporal Frequency-Transformer for Video Super-Resolution

Zhongwei Qiu, Huan Yang, Jianlong Fu, Daochang Liu, Chang Xu, Dongmei Fu

TPAMI 2023 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 20 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
learn in frequency domain with CNN instead of pixel domain (ablation)BasicVSR · REDS4 compressed CRF25PSNR: 25.93 -> 26.87Improved
use Transformer instead of CNN in frequency domain (ablation)Frequency + CNN · REDS4 compressed CRF25PSNR: 26.87 -> 27.15Improved
add frequency attention in place of vanilla attention (ablation)Frequency + Transformer · REDS4 compressed CRF25PSNR: 27.15 -> 27.28Improved
add dual frequency attention instead of local frequency attention (ablation)FTVSR · REDS CRF25PSNR: 27.23 -> 27.53Improved
add dual frequency attention instead of global frequency attention (ablation)FTVSR · REDS blur downsampling (BD)PSNR: 35.87 -> 36.33Improved
add dual frequency attention instead of local frequency attention (ablation)FTVSR · REDS random Gaussian noise 15PSNR: 26.05 -> 26.35Improved
use global instead of local frequency attention (ablation)FTVSR · REDS CRF25PSNR: 27.23 -> 27.14Hurt
add space-then-time divided frequency attention (Lambda_ST) to base attention (ablation)Frequency + Transformer · REDS CRF35PSNR: 24.03 -> 24.22Improved
add time-only frequency attention (Lambda_T) to base attention (ablation)Frequency + Transformer · REDS CRF25PSNR: 27.15 -> 27.11No clear effect
order space-frequency before time-frequency attention (Lambda_ST vs Lambda_TS) (ablation)FTVSR · REDS CRF25PSNR: 27.24 -> 27.28Improved
replace TTVSR with FTVSRTTVSR · REDS4 uncompressed 4xPSNR: 32.12 -> 32.42Improved
replace COMISR with FTVSR on compressed videosCOMISR · REDS4 compressed CRF25PSNR: 26.47 -> 28.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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