AI Paper Atlas

Research map / Image generation / Editing and style transfer

Model-based occlusion disentanglement for image-to-image translation

Fabio Pizzati, Pietro Cerri, Raoul de Charette

ECCV 2020 · Image generation › Editing and style transfer · approach: Image-to-image translation · 17 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 adversarial disentanglement with injected physical raindrop model to MUNIT backboneMUNIT · nuScenes clear-to-rainIS: 1.211 -> 1.532Improved
add adversarial disentanglement with injected physical raindrop model to MUNIT backboneMUNIT · nuScenes clear-to-rainLPIPS diversity: 0.495 -> 0.515Improved
add adversarial disentanglement with injected physical raindrop model to MUNIT backboneMUNIT · nuScenes clear-to-rainCIS: 1.030 -> 1.148Improved
use our translated rainy Cityscapes images instead of physics-based rain rendering for finetuningPSPNet · Rainy nuScenes semantic segmentationAP: 25.6 -> 27.7Improved
finetune with our rainy images vs original weightsPSPNet · Rainy nuScenes semantic segmentationAP: 18.7 -> 27.7Improved
use the full raindrop occlusion model instead of the simpler Refract or Gaussian models (ablation)Ours · nuScenes clear-to-rainGAN metricsImproved
use the matching occlusion model (drop) rather than watermark, dirt or fence models (ablation)Ours · RobotCar real raindropsFID: 329.17 -> 135.32Improved
use the drop model instead of the fence model (ablation)Ours · RobotCar real raindropsFID: 948.71 -> 135.32Improved
add disentanglement guidance with beta 0.75 versus no guidance (beta 1) (ablation)Ours · nuScenes clear-to-rainqualitativeImproved
set guidance beta to 0 (no occlusions injected) versus beta 0.75 (ablation)Ours · nuScenes clear-to-rainqualitativeHurt
use estimated defocus sigma 3.87 versus other tested sigma values (ablation)Ours · RobotCarFIDImproved
use our parameter estimation for rendered drops instead of prior drop renderingOurs · RobotCarFID and LPIPS distanceImproved

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