AI Paper Atlas

Research map / Video / Video segmentation and tracking

DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video

Zhimeng Zhang, Zhipeng Hu, Wenjin Deng, Changjie Fan, Tangjie Lv, Yu Ding

AAAI 2023 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 61 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
Use DINet instead of the strongest reported baseline on visual qualityFace visually dubbing · HDTFSSIM: 0.9078 -> 0.9425Improved
Use DINet instead of the strongest reported baseline on visual qualityFace visually dubbing · HDTFLPIPS: 0.0576 -> 0.0289Improved
Use DINet instead of the strongest reported baseline on visual qualityFace visually dubbing · MEAD-NeutralSSIM: 0.8994 -> 0.9204Improved
Use DINet instead of the strongest reported baseline on visual qualityFace visually dubbing · MEAD-NeutralLPIPS: 0.0779 -> 0.0459Improved
Use DINet instead of the strongest reported baselineFace visually dubbing · HDTFLSE-D: 6.6137 -> 8.3771Hurt
Use DINet instead of the strongest reported baselineFace visually dubbing · MEAD-NeutralLSE-D: 6.0218 -> 7.5157Hurt
Add AdaAT deformation rather than removing it and using AdaIN feature injection (ablation)DINet · HDTFSSIM: 0.9147 -> 0.9425Improved
Add source-feature fusion through the inpainting part (ablation)DINet · HDTFSSIM: 0.8691 -> 0.9425Improved
Use AdaAT deformation instead of attention-based feature selection (ablation)DINet · HDTFLPIPS: 0.0433 -> 0.0289Improved
Use AdaAT deformation instead of dense flow (ablation)DINet · HDTFLPIPS: 0.0656 -> 0.0289Improved
Use AdaAT rather than dense-flow deformation on misaligned reference features (ablation)DINet · HDTFPSNR: 23.5656 -> 30.0082Improved

Later papers that compared with this method

1 later accepted paper reports DINet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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