AI Paper Atlas

Research map / Video / Video segmentation and tracking

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Rui Xie, Yinhong Liu, Penghao Zhou, Chen Zhao, Jun Zhou, Kai Zhang, Zhenyu Zhang, Jian Yang, Zhenheng Yang, Ying Tai

ICCV 2025 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 53 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 LIEM on spatial blocks (ablation)STAR · UDM10PSNR: 23.14 -> 23.61Improved
add LIEM on temporal blocks (ablation)STAR · UDM10PSNR: 23.14 -> 23.65Improved
add LIEM on both spatial and temporal blocks (ablation)STAR · UDM10LPIPS: 0.2015 -> 0.1943Improved
insert LIEM at position (i) instead of (ii) (ablation)STAR · UDM10LPIPS: 0.2363 -> 0.1943Improved
insert LIEM at position (i) instead of (iii) (ablation)STAR · UDM10Ewarp (x1e-3): 2.74 -> 1.99Mixed
separate frequencies with direct-type DF loss (ablation)STAR · UDM10LPIPS: 0.1943 -> 0.1903Improved
use inverse instead of direct weighting of frequencies (ablation)STAR · UDM10Ewarp (x1e-3): 2.69 -> 2.83Hurt
use alpha 2 instead of 1 in c(t) with linear b(t) (ablation)STAR · UDM10LPIPS: 0.1903 -> 0.1885Improved
use exponential b(t) instead of linear with alpha 2 (ablation)STAR · UDM10LPIPS: 0.1885 -> 0.1990Hurt
increase DF loss weight beta from 1.0 to 2.0 (ablation)STAR · UDM10PSNR: 23.91 -> 24.41Mixed
decrease DF loss weight beta from 1.0 to 0.25 (ablation)STAR · UDM10LPIPS: 0.1885 -> 0.1825Mixed
scale T2V backbone from CogVideoX-2B to CogVideoX-5B (ablation)STAR · OpenVid cropped 480x720SSIM: 0.7112 -> 0.7400Improved

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