Research map / Image generation / Editing and style transfer
Unsupervised Person Image Synthesis in Arbitrary Poses
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Replace the identity loss with standard L1 loss (ablation) | Unsupervised person image synthesis model · DeepFashion | Person identity preservation | Hurt |
| Add adversarial and pose losses for the recovered image (ablation) | Unsupervised person image synthesis model · Training | Training robustness and convergence | Helped |
| Add patch-style loss to preserve texture around visible joints (ablation) | Unsupervised person image synthesis model · DeepFashion pose synthesis | High-frequency texture detail | Helped |
Closest papers by meaning
- Person Image Synthesis via Denoising Diffusion Model (CVPR 2023 · similarity 0.91)
- Pose Guided Person Image Generation (NeurIPS 2017 · similarity 0.91)
- Synthesizing Images of Humans in Unseen Poses (CVPR 2018 · similarity 0.90)
- Deformable GANs for Pose-Based Human Image Generation (CVPR 2018 · similarity 0.90)
- Progressive Pose Attention Transfer for Person Image Generation (CVPR 2019 · similarity 0.89)
- Multistage Adversarial Losses for Pose-Based Human Image Synthesis (CVPR 2018 · similarity 0.89)
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.