atlas

Research map / Video / Video segmentation and tracking

BasicVSR++: Improving Video Super-Resolution With Enhanced Propagation and Alignment

CVPR 2022 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 586 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Replace IconVSR with BasicVSR++Video super-resolution · REDS4 BIPSNR (dB): 31.67 -> 32.39Helped
Add flow-guided deformable alignment (ablation)BasicVSR++ · REDS4PSNR (dB): 31.48 -> 31.94Helped
Add second-order propagation (ablation)BasicVSR++ · REDS4PSNR (dB): 31.94 -> 32.08Helped
Add grid propagation (ablation)BasicVSR++ · REDS4PSNR (dB): 32.08 -> 32.39Helped
Remove optical-flow guidance from deformable alignment (ablation)BasicVSR++ · REDS4PSNR (dB): 32.39 -> 27.44Hurt
Use optical flow only as offset-fidelity loss supervision rather than as base offsets (ablation)BasicVSR++ · REDS4PSNR (dB): 32.39 -> 30.22Hurt
Increase propagation orders or iterations beyond two (ablation)BasicVSR++ · REDS4PSNR (dB): 0.05 dBNo clear effect

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