AI Paper Atlas

Research map / 3D vision / Human pose estimation

Human Synthesis and Scene Compositing

Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Andrei Zanfir, Cristian Sminchisescu

AAAI 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 22 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 a learned displacement field instead of no displacement field (ablation)HUSC-S · DeepFashionIS: 3.3876 -> 3.6343Improved
Use a learned displacement field instead of no displacement field (ablation)HUSC-S · DeepFashionSSIM: 0.8035 -> 0.8049Improved
Add a fixed body-only displacement field (ablation)HUSC-S without displacement field · DeepFashionIS: 3.3876 -> 3.4541Improved
Add a fixed body-only displacement field (ablation)HUSC-S without displacement field · DeepFashionSSIM: 0.8035 -> 0.8016Hurt
Replace fixed body-only displacement with learned displacement extended to clothing and hair (ablation)HUSC-S · DeepFashionIS: 3.4541 -> 3.6343Improved
Replace fixed body-only displacement with learned displacement extended to clothing and hair (ablation)HUSC-S · DeepFashionSSIM: 0.8016 -> 0.8049Improved
Add full-method components, including deformable skip connections and target dense pose in decoding (ablation)HUSC-S with learned displacement field · DeepFashionIS: 3.6343 -> 3.6950Improved
Add full-method components, including deformable skip connections and target dense pose in decoding (ablation)HUSC-S with learned displacement field · DeepFashionSSIM: 0.8049 -> 0.8135Improved
Refine perturbed composites with L1 and VGG lossesAppearance Compositing · COCO validation (1000 images)LPIPS, full image: 0.0971 ± 0.0596 -> 0.0588 ± 0.0267Improved
Refine perturbed composites with L1 and VGG lossesAppearance Compositing · COCO validation (1000 images)LPIPS, foreground: 0.2569 ± 0.0811 -> 0.1317 ± 0.0514Improved
Add discriminator GAN loss to appearance compositing (ablation)Appearance Compositing (L1+VGG) · COCO validation (1000 images)LPIPS, full image: 0.0588 ± 0.0267 -> 0.0542 ± 0.0243Improved
Add discriminator GAN loss to appearance compositing (ablation)Appearance Compositing (L1+VGG) · COCO validation (1000 images)LPIPS, foreground: 0.1317 ± 0.0514 -> 0.1165 ± 0.0480Improved

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