Research map / Image generation / Editing and style transfer
TIPS: Text-Induced Pose Synthesis
Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add regressive keypoint refinement (ablation) | text-guided pose transfer · DeepFashion | SSIM: 0.545 -> 0.549 | Improved |
| add regressive keypoint refinement (ablation) | text-guided pose transfer · DeepFashion | IS: 3.261 -> 3.296 | Improved |
| add regressive keypoint refinement (ablation) | text-guided pose transfer · DeepFashion | GCR: 0.960 -> 0.963 | Improved |
| add multi-scale attention instead of single-scale (ablation) | partially text-guided generator · DeepFashion | SSIM: 0.540 -> 0.549 | Improved |
| add multi-scale attention instead of single-scale (ablation) | partially text-guided generator · DeepFashion | IS: 3.170 -> 3.269 | Improved |
| add multi-scale attention instead of single-scale (ablation) | partially text-guided generator · DeepFashion | DS: 0.921 -> 0.950 | Improved |
| add multi-scale attention instead of single-scale (ablation) | partially text-guided generator · DeepFashion | PCKh: 0.54 -> 0.53 | Hurt |
| swap BERT for FastText (ablation) | text encoder · DeepFashion | SSIM: 0.549 -> 0.548 | No clear effect |
| swap BERT for Word2Vec (ablation) | text encoder · DeepFashion | GCR: 0.963 -> 0.973 | No clear effect |
| use multi-hot encoding instead of BERT (ablation) | text encoder · DeepFashion | SSIM: 0.549 -> 0.558 | No clear effect |
| describe source pose with text instead of keypoints | text-guided pose transfer · DeepFashion | IS: 3.269 -> 3.296 | No clear effect |
| replace keypoint guidance (PATN) with text-guided target pose | PATN · Real-world target poses | SSIM: 0.677 -> 0.696 | Improved |
Closest papers by meaning
- Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation (NeurIPS 2024 · similarity 0.88)
- Follow Your Pose: Pose-Guided Text-to-Video Generation Using Pose-Free Videos (AAAI 2024 · similarity 0.87)
- Harmonizing Visual and Textual Embeddings for Zero-Shot Text-to-Image Customization (AAAI 2025 · similarity 0.86)
- PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose Manipulation (AAAI 2025 · similarity 0.86)
- FlexPose: Pose Distribution Adaptation with Limited Guidance (AAAI 2025 · similarity 0.85)
- UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing (CVPR 2025 · similarity 0.85)
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.
