Research map / 3D vision / Face and shape
Learning an Isometric Surface Parameterization for Texture Unwrapping
Sagnik Das, Ke Ma, Zhixin Shu, Dimitris Samaras
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 single-image DewarpNet with multi-view implicit surface parameterization | Isometric UV-field texture unwrapping · Synthetic (all views) | Local distortion: 7.81 -> 4.31 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Synthetic (all views) | MS-SSIM: 0.5382 -> 0.6302 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Synthetic (frontal view) | Local distortion: 5.37 -> 4.02 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Synthetic (frontal view) | MS-SSIM: 0.5965 -> 0.6405 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Real (all views) | Local distortion: 10.25 -> 7.16 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Real (all views) | MS-SSIM: 0.4601 -> 0.4951 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Real (frontal view) | Local distortion: 7.85 -> 6.28 | Improved |
| replace DewarpNet with the proposed method | Isometric UV-field texture unwrapping · Real (frontal view) | MS-SSIM: 0.4724 -> 0.494 | No clear effect |
| unwarp with the proposed method before OCR instead of DewarpNet | Isometric UV-field texture unwrapping · OCR (5 real scenes) | Edit distance: 798.30 -> 600.78 | Improved |
| unwarp with the proposed method before OCR instead of DewarpNet | Isometric UV-field texture unwrapping · OCR (5 real scenes) | Character error rate: 0.2827 -> 0.2122 | Improved |
| unwarp with the proposed method before OCR instead of DewarpNet | Isometric UV-field texture unwrapping · OCR (5 real scenes) | Word error rate: 0.4646 -> 0.3568 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DewarpNet — DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks (ICCV 2019) · better on 11 of 11 shared results
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
- Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering (ECCV 2024 · similarity 0.88)
- Unsupervised Representation Learning for 3D Mesh Parameterization with Semantic and Visibility Objectives (ICLR 2026 · similarity 0.88)
- AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis (CVPR 2022 · similarity 0.87)
- NeuTex: Neural Texture Mapping for Volumetric Neural Rendering (CVPR 2021 · similarity 0.87)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.86)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.86)
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.
