# Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

arXiv: https://arxiv.org/abs/1706.07036 · HTML: https://mlsanity.com/paper/1706.07036/

## Key facts

- Cited by 133 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2017.

## Built on by (most cited first, 30 of 133)

- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [NeRF-Art: Text-Driven Neural Radiance Fields Stylization](https://mlsanity.com/paper/2212.08070/) (2022)
- [Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting](https://mlsanity.com/paper/2403.15530/) (2024)
- [Neural Kernel Surface Reconstruction](https://mlsanity.com/paper/2305.19590/) (2023)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [The Power of Points for Modeling Humans in Clothing](https://mlsanity.com/paper/2109.01137/) (2021)
- [What's in your hands? 3D Reconstruction of Generic Objects in Hands](https://mlsanity.com/paper/2204.07153/) (2022)
- [AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control](https://mlsanity.com/paper/2303.17606/) (2023)
- [SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements](https://mlsanity.com/paper/2104.07660/) (2021)
- [DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images](https://mlsanity.com/paper/2208.07227/) (2022)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [Neural Fields as Learnable Kernels for 3D Reconstruction](https://mlsanity.com/paper/2111.13674/) (2021)
- [Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections](https://mlsanity.com/paper/2307.08093/) (2023)
- [Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images](https://mlsanity.com/paper/2503.13439/) (2025)
- [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://mlsanity.com/paper/2207.06955/) (2022)
- [NeuPhysics: Editable Neural Geometry and Physics from Monocular Videos](https://mlsanity.com/paper/2210.12352/) (2022)
- [Vox-Surf: Voxel-based Implicit Surface Representation](https://mlsanity.com/paper/2208.10925/) (2022)
- [Point-set Distances for Learning Representations of 3D Point Clouds](https://mlsanity.com/paper/2102.04014/) (2021)
- [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://mlsanity.com/paper/2203.15190/) (2022)
- [Approximate Differentiable Rendering with Algebraic Surfaces](https://mlsanity.com/paper/2207.10606/) (2022)

## Abstract (arXiv)

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in attempt to predict 3D shapes, where information is rich only on the surfaces. In this paper, we propose a novel 3D generative modeling framework to efficiently generate object shapes in the form of dense point clouds. We use 2D convolutional operations to predict the 3D structure from multiple viewpoints and jointly apply geometric reasoning with 2D projection optimization. We introduce the pseudo-renderer, a differentiable module to approximate the true rendering operation, to synthesize novel depth maps for optimization. Experimental results for single-image 3D object reconstruction tasks show that we outperforms state-of-the-art methods in terms of shape similarity and prediction density.