AI Paper Atlas

Research map / Video / Video segmentation and tracking

TAQ: Static-Deployable Temporal-Aware Quantization for Real-World Video Super-Resolution

Jinwoo Chung, Sangho An, Sungyeop Jung, Jangho Kim

ECCV 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 0 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 sequence-wise calibration with bound ensembling (ablation)TAQ on RealViformer · REDS (4-bit)PSNR: 23.1268 -> 23.8104 (PSNR rises by 0.68 dB)Improved
add sequence-wise calibration with bound ensembling (ablation)TAQ on RealViformer · REDS (4-bit)TLPIPS: 15.3454 -> 11.3696Improved
add sequence-wise calibration with bound ensembling (ablation)TAQ on RealViformer · REDS (4-bit)TOF: 55.4030 -> 27.5246Improved
add temporal refinement with temporal consistency loss (ablation)TAQ on RealViformer · REDS (4-bit)TLPIPS: 11.3696 -> 10.0249Improved
add temporal refinement with temporal consistency loss (ablation)TAQ on RealViformer · REDS (4-bit)PSNR: 23.8104 -> 23.8949Improved
add 99.9% percentile clipping (ablation)TAQ on RealViformer · REDS (4-bit)PSNR: 22.6066 -> 23.8949Improved
add 99.9% percentile clipping (ablation)2DQuant on RealViformer · REDS (4-bit)TLPIPS: 17.8592 -> 12.9041Improved
use arithmetic mean instead of median for bound ensembling (ablation)TAQ on RealViformer · REDS (4-bit)PSNR: 23.0800 -> 23.8949Improved
use arithmetic mean instead of trimmed mean for bound ensembling (ablation)TAQ on RealViformer · REDS (4-bit)PSNR: 23.8851 -> 23.8949No clear effect
use learned aggregation weights instead of uniform mean (ablation)TAQ on RealViformer · REDS (4-bit)TLPIPS: 10.0249 -> 10.2315 (PSNR 23.8949 -> 23.8996)Hurt
use TAQ instead of 2DQuant with only 5 calibration sequencesTAQ vs 2DQuant · REDS (4/4-bit, 5 calib seqs)TLPIPS: 14.09 -> 10.20Improved
use TAQ instead of 2DQuant on RealBasicVSR backboneTAQ vs 2DQuant · REDS (4-bit, RealBasicVSR)TLPIPS: 5.4051 -> 4.2680Improved

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