Research map / Video / Video segmentation and tracking
Online Video Quality Enhancement with Spatial-Temporal Look-up Tables
Zefan Qu, Xinyang Jiang, Yifan Yang, Dongsheng Li, Cairong Zhao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| select reference frames by lowest QP in the reference window instead of randomly (ablation) | STLVQE · MFQE 2.0 (QP=37) | Delta PSNR: +0.03 dB, +0.33 ms | Improved |
| add Temporal Cache for reusing reference features (ablation) | STLVQE · MFQE 2.0 (720P, QP=37) | runtime per frame: 45.61 -> 24.65 ms | Improved |
| add deform operation for reference alignment (ablation) | STLVQE · MFQE 2.0 (QP=37) | Delta PSNR: 0.06 -> 0.31 | Improved |
| add preliminary complement (spatial compensation) residual (ablation) | STLVQE · MFQE 2.0 (QP=37) | Delta PSNR: 0.31 -> 0.49 | Improved |
| add T-LUT-2 alongside T-LUT-1 (ablation) | ST-LUTs · MFQE 2.0 (QP=37) | Delta PSNR: 0.45 -> 0.47 (+0.08 vs S-LUT+T-LUT-1 stated) | Improved |
| apply ST-LUTs on compensated frame instead of original frame (ablation) | ST-LUTs · MFQE 2.0 (QP=37) | Delta PSNR: 0.47 -> 0.49 | Improved |
| replace CNN enhancement network with ST-LUTs at inference (ablation) | STLVQE · MFQE 2.0 (720P, QP=37) | Delta PSNR and runtime: -0.01 dB, -122.37 ms | Improved |
| add T-LUT-1 to S-LUT only (ablation) | ST-LUTs · MFQE 2.0 (QP=37) | Delta PSNR: 0.39 -> 0.45 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- BasicVSR++ — BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond (CVPR 2021) · better on 0 of 1 shared result
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
- Multi-Frame Deformable Look-Up Table for Compressed Video Quality Enhancement (AAAI 2025 · similarity 0.85)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.84)
- PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement (NeurIPS 2025 · similarity 0.83)
- CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement (CVPR 2024 · similarity 0.83)
- Knowledge Guided Semi-supervised Learning for Quality Assessment of User Generated Videos (AAAI 2024 · similarity 0.83)
- Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs (CVPR 2025 · similarity 0.82)
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.
