Research map / 3D vision / Face and shape
NGD: Neural Gradient Based Deformation for Monocular Garment Reconstruction
Soham Dasgupta, Shanthika Naik, Preet Savalia, Sujay Kumar Ingle, Avinash Sharma
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 adaptive remeshing (ablation) | NGD · 4D-Dress average | Chamfer distance: 0.441 -> 0.431 | Improved |
| add adaptive remeshing (ablation) | NGD · 4D-Dress average | Normal consistency: 0.850 -> 0.853 | Improved |
| add adaptive remeshing (ablation) | NGD · 4D-Dress seq 185 | Chamfer distance: 0.372 -> 0.393 | Hurt |
| supervise with diffuse images instead of normal maps (ablation) | NGD · 4D-Dress average | Chamfer distance: 0.554 -> 0.431 | Improved |
| supervise with diffuse images instead of normal maps (ablation) | NGD · 4D-Dress average | Normal consistency: 0.832 -> 0.853 | Improved |
| use gradient-based deformation instead of per-vertex displacement (DGarment) | NGD · 4D-Dress seq 187 | Chamfer distance: 1.722 -> 0.923 | Improved |
| use explicit mesh with neural gradient deformation instead of implicit SCARF | NGD · 4D-Dress average | Chamfer distance: 5.203 -> 0.431 | Improved |
| use NGD with dynamic textures instead of SCARF | NGD · 4D-Dress seq 123 | PSNR: 43.02 -> 46.78 | Improved |
| use NGD instead of SCARF | NGD · 4D-Dress seq 187 | PSNR: 25.32 -> 25.85 | Improved |
| use NGD instead of SCARF | NGD · 4D-Dress seq 187 | LPIPS: 0.0828 -> 0.0395 | Improved |
| use NGD instead of DGarment | NGD · 4D-Dress average | Normal consistency: 0.833 -> 0.853 | Improved |
Closest papers by meaning
- REC-MV: REconstructing 3D Dynamic Cloth From Monocular Videos (CVPR 2023 · similarity 0.92)
- Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates (TPAMI 2026 · similarity 0.90)
- Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models (CVPR 2024 · similarity 0.89)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.88)
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.88)
- Reconstruction of Manipulated Garment with Guided Deformation Prior (NeurIPS 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.
