# Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

arXiv: https://arxiv.org/abs/1803.08908 · HTML: https://mlsanity.com/paper/1803.08908/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2018.

## Built on by (most cited first, 11 of 11)

- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [A Survey of Non-Rigid 3D Registration](https://mlsanity.com/paper/2203.07858/) (2022)
- [State of the Art in Dense Monocular Non-Rigid 3D Reconstruction](https://mlsanity.com/paper/2210.15664/) (2022)
- [InstructionBench: An Instructional Video Understanding Benchmark](https://mlsanity.com/paper/2504.05040/) (2025)
- [Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks](https://mlsanity.com/paper/2306.04701/) (2023)
- [Modeling 3D Surface Manifolds with a Locally Conditioned Atlas](https://mlsanity.com/paper/2102.05984/) (2021)
- [Deformable Surface Reconstruction via Riemannian Metric Preservation](https://mlsanity.com/paper/2212.11596/) (2022)
- [Textureless Deformable Surface Reconstruction with Invisible Markers](https://mlsanity.com/paper/2308.13678/) (2023)
- [Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation](https://mlsanity.com/paper/2406.15831/) (2024)
- [SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration](https://mlsanity.com/paper/2409.14474/) (2024)
- [A 3D Generation Framework from Cross Modality to Parameterized Primitive](https://mlsanity.com/paper/2510.08656/) (2025)

## Abstract (arXiv)

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, and essentially relates to Shape-from-Shading. In this paper, we introduce a data-driven approach to this problem. We introduce a general framework that can predict diverse 3D representations, such as meshes, normals, and depth maps. Our experiments show that meshes are ill-suited to handle texture-less 3D reconstruction in our context. Furthermore, we demonstrate that our approach generalizes well to unseen objects, and that it yields higher-quality reconstructions than a state-of-the-art SfS technique, particularly in terms of normal estimates. Our reconstructions accurately model the fine details of the surfaces, such as the creases of a T-Shirt worn by a person.