# CD2: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distance

arXiv: https://arxiv.org/abs/2206.00447 · HTML: https://mlsanity.com/paper/2206.00447/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](https://mlsanity.com/paper/1804.04610/) (2018)
- [Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild](https://mlsanity.com/paper/1911.11130/) (2019)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019)
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://mlsanity.com/paper/1706.07036/) (2017)
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://mlsanity.com/paper/2111.12702/) (2021)
- [Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks](https://mlsanity.com/paper/1909.00321/) (2019)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds](https://mlsanity.com/paper/1904.00229/) (2019)
- [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://mlsanity.com/paper/2203.15190/) (2022)
- [Image2Mesh: A Learning Framework for Single Image 3D Reconstruction](https://mlsanity.com/paper/1711.10669/) (2017)
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://mlsanity.com/paper/2205.06267/) (2022)
- [Which priors matter? Benchmarking models for learning latent dynamics](https://mlsanity.com/paper/2111.05458/) (2021)
- [DPDist : Comparing Point Clouds Using Deep Point Cloud Distance](https://mlsanity.com/paper/2004.11784/) (2020)
- [Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering](https://mlsanity.com/paper/1905.04571/) (2019)
- [LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds](https://mlsanity.com/paper/1904.10037/) (2019)
- [A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization](https://mlsanity.com/paper/1906.11478/) (2019)
- [GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion](https://mlsanity.com/paper/1911.06600/) (2019)
- [DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction](https://mlsanity.com/paper/1911.09204/) (2019)
- [Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector](https://mlsanity.com/paper/2010.00321/) (2020)

## Built on by (most cited first, 1 of 1)

- [Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation](https://mlsanity.com/paper/2403.01619/) (2024)

## Abstract (arXiv)

Monocular 3D reconstruction is to reconstruct the shape of object and its other information from a single RGB image. In 3D reconstruction, polygon mesh, with detailed surface information and low computational cost, is the most prevalent expression form obtained from deep learning models. However, the state-of-the-art schemes fail to directly generate well-structured meshes, and we identify that most meshes have severe Vertices Clustering (VC) and Illegal Twist (IT) problems. By analyzing the mesh deformation process, we pinpoint that the inappropriate usage of Chamfer Distance (CD) loss is a root cause of VC and IT problems in deep learning model. In this paper, we initially demonstrate these two problems induced by CD loss with visual examples and quantitative analyses. Then, we propose a fine-grained reconstruction method CD2 by employing Chamfer distance twice to perform a plausible and adaptive deformation. Extensive experiments on two 3D datasets and comparisons with five latest schemes demonstrate that our CD2 directly generates a well-structured mesh and outperforms others in terms of several quantitative metrics.