Research map / 3D vision / Face and shape
Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images
Heming Zhu, Lingteng Qiu, Yuda Qiu, Xiaoguang Han
Check 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 |
|---|---|---|---|
| Register explicit garment templates to pixel-aligned implicit clothed-human fields | ReEF · Synthetic testing set | CD (×10⁻³): 0.9725 -> 0.5477 | Improved |
| Add curve-aligned heatmap guidance to boundary-field generation (ablation) | ReEF boundary-field generation · Garment boundary generation | CD (×10⁻³): 6.3786 -> 1.1073 | Improved |
| Replace the proposed boundary fields with Point Transformer parsing of dense point clouds | Garment boundary generation · Garment boundary generation | CD (×10⁻³): 1.1073 -> 6.5329 | Hurt |
| Replace the proposed boundary fields with image-guided graph convolution curve regression | Garment boundary generation · Garment boundary generation | CD (×10⁻³): 1.1073 -> 9.18467 | Hurt |
| Remove pose initialization (ablation) | ReEF explicit fitting · Garment mesh registration | Dist (×10⁻³): 3.41651 -> 3.52109 | Hurt |
| Remove boundary initialization (ablation) | ReEF explicit fitting · Garment mesh registration | Dist (×10⁻³): 3.41651 -> 70.3211 | Hurt |
| Remove active area probing (ablation) | ReEF explicit fitting · Garment mesh registration | Dist (×10⁻³): 3.41651 -> 3.56883 | Hurt |
| Use only pixel-aligned coarse shape features for boundary generation (ablation) | ReEF boundary-field generation · Garment boundary generation | CD (×10⁻³): 1.1073 -> 6.3786 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SMPLicit — SMPLicit: Topology-Aware Generative Model for Clothed People (CVPR 2021) · better on 1 of 1 shared result
- BCNet — BCNet: Learning Body and Cloth Shape from A Single Image (ECCV 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Spatio-Temporal Garment Reconstruction Using Diffusion Mapping via Pattern Coordinates (TPAMI 2026 · similarity 0.91)
- Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images (ECCV 2020 · similarity 0.90)
- Garment4D: Garment Reconstruction from Point Cloud Sequences (NeurIPS 2021 · similarity 0.90)
- DeepCloth: Neural Garment Representation for Shape and Style Editing (TPAMI 2022 · similarity 0.90)
- ReWeaver: Towards Simulation-Ready and Topology-Accurate Garment Reconstruction (CVPR 2026 · similarity 0.90)
- CloSET: Modeling Clothed Humans on Continuous Surface With Explicit Template Decomposition (CVPR 2023 · similarity 0.90)
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.
