AI Paper Atlas

Research map / Video / Video segmentation and tracking

An Internal Learning Approach to Video Inpainting

Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin

ICCV 2019 · Video › Video segmentation and tracking · approach: Learned optical flow estimation · 83 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
train on whole video instead of frame-wise DIP (ablation)DIP · Composed dataset (250 videos)FID: 22.3 -> 16.1Improved
train on whole video instead of frame-wise DIP (ablation)DIP · Composed dataset (250 videos)PSNR: 25.2 -> 28.7Improved
replace 2D with 3D convolution (ablation)DIP-Vid · Composed dataset (250 videos)FID: 16.1 -> 12.1Improved
replace 2D with 3D convolution (ablation)DIP-Vid · Composed dataset (250 videos)PSNR: 28.7 -> 30.9Improved
add flow prediction with consistency loss to 2D network (ablation)DIP-Vid · Composed dataset (250 videos)FID: 16.1 -> 10.4Improved
add flow prediction with consistency loss, versus 3D convolution (ablation)DIP-Vid-3DCN · Composed dataset (250 videos)temporal consistency PSNR: 26.7 -> 28.1Improved
add flow prediction with consistency loss (ablation)DIP-Vid · Composed dataset (250 videos)PSNR: 28.7 -> 32.1Improved
use internal learning instead of Huang et al. patch-based method (all videos)Huang et al. · Composed dataset (All)PSNR: 32.3 -> 32.1No clear effect
use internal learning instead of Huang et al. on complex-motion videosHuang et al. · Composed dataset (Complex)PSNR: 31.6 -> 31.9Improved
use internal learning instead of Huang et al. on simple videosHuang et al. · Composed dataset (Simple)PSNR: 33.0 -> 32.2Hurt
increase input window length k (ablation)DIP-Vid-Flow · 10 Composed videos, window length 1 to 100inpainting quality (full frame)Improved
increase input window length k (ablation)DIP-Vid-Flow · 10 Composed videos, window length 1 to 100non-hole reconstruction qualityHurt

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