AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution

Zixi Tuo, Huan Yang, Jianlong Fu, Yujie Dun, Xueming Qian

ICCV 2023 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 10 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
replace basic-operator-only degradation with VQ degradation codebook (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3768 -> 0.3857Improved
use multi-scale VQGAN instead of single-scale (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3466 -> 0.3857Improved
use two-stage training for multi-scale VQGAN instead of single-stage (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3430 -> 0.3857Improved
use stochastic top-k VQ instead of nearest-neighbor search (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3770 -> 0.3857Improved
increase max degradation level K in top-k from 50 to 100 (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3857 -> 0.3756Hurt
add VQ degradation to Real-ESRGAN* backboneReal-ESRGAN* · AVC-RealLQMANIQA: 0.3825 -> 0.3967Improved
add VQ degradation to RealBasicVSR* backboneRealBasicVSR* · AVC-RealLQMANIQA: 0.3504 -> 0.3849Improved
add VQ degradation to AnimeSR backboneAnimeSR · AVC-RealLQMANIQA: 0.3832 -> 0.3857Improved
add HR-SR enhancement of training HR videos (Real-ESRGAN S) (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.3857 -> 0.4096Improved
add HR-SR enhancement when training RealBasicVSRRealBasicVSR · AVC-RealLQMANIQA: 0.3504 -> 0.3855Improved
add HR-SR enhancement when training AnimeSRAnimeSR · AVC-RealLQMANIQA: 0.3832 -> 0.4079Improved
use larger Real-ESRGAN (L) instead of small (S) for HR enhancement (ablation)VQD-SR (base) · AVC-RealLQMANIQA: 0.4096 -> 0.4211Improved

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