AI Paper Atlas

Research map / Video / Video generation

Long-Term Temporally Consistent Unpaired Video Translation From Simulated Surgical 3D Data

Dominik Rivoir, Micha Pfeiffer, Reuben Docea, Fiona Kolbinger, Carina Riediger, Jürgen Weitz, Stefanie Speidel

ICCV 2021 · Video › Video generation · approach: Trajectory-guided motion control · 42 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 neural textures (without view-consistency loss) (ablation)Ours w/o tex,vc · Simulated surgical scenesORB-1 match accuracy: 81.7% -> 88.3%Improved
add neural textures (without view-consistency loss) (ablation)Ours w/o tex,vc · Simulated surgical scenesORB-10 match accuracy: 29.5% -> 44.5%Improved
add neural textures (without view-consistency loss) (ablation)Ours w/o tex,vc · Simulated surgical scenesoptical-flow error (OF): 8.43 -> 8.35Improved
add neural textures (without view-consistency loss) (ablation)Ours w/o tex,vc · Simulated surgical scenesFID: 27.3 -> 27.0No clear effect
add neural textures (without view-consistency loss) (ablation)Ours w/o tex,vc · Simulated surgical scenesliver segmentation Dice (%): 56.8 -> 55.2Hurt
add lighting-invariant view-consistency loss (ablation)Ours w/o vc · Simulated surgical scenesoptical-flow error (OF): 8.35 -> 7.62Improved
add lighting-invariant view-consistency loss (ablation)Ours w/o vc · Simulated surgical scenesORB-10 match accuracy: 44.5% -> 49.6%Improved
add lighting-invariant view-consistency loss (ablation)Ours w/o vc · Simulated surgical scenesORB-1 match accuracy: 88.3% -> 91.8%Improved
remove style and noise injection from the generator (SSIM-MUNIT to Ours w/o tex,vc) (ablation)SSIM-MUNIT · Simulated surgical scenesORB-1 match accuracy: 60.5% -> 81.7%Improved
add MS-SSIM loss for label preservation (ReCycle to SSIM-ReCycle)ReCycle · Simulated surgical scenesliver segmentation Dice (%): 40.7 -> 50.9Improved
add MS-SSIM loss for label preservation (ReCycle to SSIM-ReCycle)ReCycle · Simulated surgical scenesFID: 61.5 -> 80.6Hurt
revisit earlier views instead of consecutive framesOF-UNIT · Simulated surgical scenesORB-1 match accuracy: 93.5% -> 69.9%Hurt

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