AI Paper Atlas

Research map / Video / Video segmentation and tracking

LDIP: Long Distance Information Propagation for Video Super-Resolution

Michael Bernasconi, Abdelaziz Djelouah, Yang Zhang, Markus Gross, Christopher Schroers

ICCV 2025 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 1 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 LRRF module trained with HQ references (vs HRIP only) (ablation)BasicVSR++ backbone · REDS x4 ablationLPIPS: 0.129 -> 0.106Improved
add LRRF module trained with HQ references (vs HRIP only) (ablation)BasicVSR++ backbone · REDS x4 ablationPSNR: 32.28 -> 32.04Hurt
use HQ references instead of self-referential references (ablation)BasicVSR++ backbone · REDS x4 ablationLPIPS: 0.126 -> 0.106Improved
add self-referential references to HQ training (ablation)BasicVSR++ backbone · REDS x4 ablationLPIPS: 0.106 -> 0.126Hurt
use RAFT instead of SpyNet for HRIP flow (ablation)BasicVSR++ backbone · REDS x4 ablationLPIPS: 0.110 -> 0.107Improved
use PDCNetPlus instead of RAFT for HRIP flow (ablation)BasicVSR++ backbone · REDS x4 ablationLPIPS: 0.107 -> 0.106No clear effect
replace upscaling layer with arbitrary scaling module (ablation)BasicVSR++ · REDS x4 ablationPSNR: 32.41 -> 32.13Hurt
add long range propagation on top of arbitrary scaling (ablation)BasicVSR++ with AS · REDS x4 ablationLPIPS: 0.129 -> 0.113Improved
add long range propagation on top of arbitrary scaling (ablation)BasicVSR++ with AS · REDS x4 ablationPSNR: 32.13 -> 31.67Hurt
add LDIP to IART backboneIART · REDS x4LPIPS: 0.105 -> 0.097Improved
add LDIP to IART backboneIART · REDS x4PSNR: 33.20 -> 32.83Hurt
5 references every 5 frames instead of every 1 (ablation)Ours (IART) · REDS x4 key-frame densitymemory (GB): 31.1 -> 22.0Improved

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