AI Paper Atlas

Research map / Video / Video generation

Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal

Radim Špetlík, David Futschik, Radek Danecek, Feitong Tan, Ziqian Bai, Rohit Pandey, Yinda Zhang

ECCV 2026 · Video › Video generation · approach: Diffusion-based video editing · 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 global skip connection (CNN-CNN) (ablation)CNN-CNN restoration net · FFHQ clear glassesFID: 0.493 -> 0.439Improved
add global skip connection (ViT-CNN) (ablation)JFSnet · FFHQ clear glassesFID: 0.387 -> 0.379Improved
unfreeze last four DINOv2 layers (ViT-ViT, no skip) (ablation)ViT-ViT · FFHQ clear glassesFID: 1.131 -> 0.572Improved
unfreeze last four DINOv2 layers (ViT-ViT, with skip) (ablation)ViT-ViT · FFHQ clear glassesFID: 0.384 -> 0.392Hurt
use CNN decoder instead of ViT decoder (ablation)JFSnet · FFHQ clear glassesFID: 0.392 -> 0.379Improved
use ViT encoder with CNN decoder instead of CNN-only (ablation)JFSnet · FFHQ clear glassesFID: 0.439 -> 0.379Improved
add physics-based refraction and reflection simulation (ablation)JFSnet · FFHQ clear glassesFIDImproved
add translation-equivariance temporal loss (ablation)JFSnet · CelebV-TextRAFT-L1: 8.023 -> 7.682Improved
add translation-equivariance temporal loss (ablation)JFSnet · CelebV-TexttLPIPS: 19.520 -> 18.528Improved
add translation-equivariance temporal loss (ablation)JFSnet · 300-identity paired setSSIM: 0.947 -> 0.950No clear effect
retrain TOE on JFSnet training dataTake-Off-Eyeglasses · 300-identity paired set, lens regionPSNR: 18.98 -> 24.19Improved
retrain ProPainter on JFSnet training dataProPainter · 300-identity paired set, lens regionPSNR: 15.28 -> 16.71Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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