Research map / 3D vision / Face and shape
ZFlow: Gated Appearance Flow-Based Virtual Try-On With 3D Priors
Ayush Chopra, Rishabh Jain, Mayur Hemani, Balaji Krishnamurthy
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 |
|---|---|---|---|
| replace ClothFlow per-pixel flow warping with Gated Appearance Flow (ablation) | ZFlow warping · VITON warp garment | SSIM: 0.835 -> 0.871 | Improved |
| replace ClothFlow warping with GAF (ablation) | ZFlow warping · VITON warp garment | PSNR: 20.54 -> 23.14 | Improved |
| replace ClothFlow warping with GAF (ablation) | ZFlow · VITON try-on | FID: 23.68 -> 18.89 | Improved |
| use ConvGRU instead of residual gating for flow aggregation (ablation) | GAF · VITON try-on | FID: 21.64 -> 18.89 | Improved |
| use ConvGRU instead of ConvLSTM for flow aggregation (ablation) | GAF · VITON try-on | SSIM: 0.860 -> 0.865 | Improved |
| add dense garment-agnostic priors and Sobel edge loss to texture fusion (ablation) | ZFlow texture fusion · VITON try-on | PSNR: 24.47 -> 25.02 | Improved |
| add edge loss L_edge (ablation) | ZFlow texture fusion · VITON try-on | SSIM: 0.865 -> 0.875 | Improved |
| add reconstruction loss L_recon on IUV priors (ablation) | ZFlow texture fusion · VITON try-on | FID: 19.39 -> 18.74 | Improved |
| add reconstruction loss L_recon on IUV priors (ablation) | ZFlow texture fusion · VITON try-on | PSNR: 25.02 -> 25.12 | Improved |
| add end-to-end fine-tuning of the whole network (ablation) | ZFlow · VITON try-on | FID: 18.74 -> 15.17 | Improved |
| add end-to-end fine-tuning of the whole network (ablation) | ZFlow · VITON try-on | SSIM: 0.876 -> 0.885 | Improved |
| add dense garment-agnostic representation to warping (ablation) | GAF · VITON warp garment | PSNR: 23.14 -> 23.28 | Improved |
Closest papers by meaning
- Style-Based Global Appearance Flow for Virtual Try-On (CVPR 2022 · similarity 0.91)
- Single Stage Virtual Try-On via Deformable Attention Flows (ECCV 2022 · similarity 0.89)
- Towards Squeezing-Averse Virtual Try-On via Sequential Deformation (AAAI 2024 · similarity 0.89)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.87)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.87)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.87)
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.
