# GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion

arXiv: https://arxiv.org/abs/1911.06600 · HTML: https://mlsanity.com/paper/1911.06600/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling](https://mlsanity.com/paper/2208.06880/) (2022)
- [PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis](https://mlsanity.com/paper/2202.04879/) (2022)
- [Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes](https://mlsanity.com/paper/2408.14279/) (2024)
- [sat2pc: Estimating Point Cloud of Building Roofs from 2D Satellite Images](https://mlsanity.com/paper/2205.12464/) (2022)
- [PU-MFA : Point Cloud Up-sampling via Multi-scale Features Attention](https://mlsanity.com/paper/2208.10968/) (2022)
- [CD2: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distance](https://mlsanity.com/paper/2206.00447/) (2022)
- [Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting](https://mlsanity.com/paper/2508.14443/) (2025)
- [AIM2PC: Aerial Image to 3D Building Point Cloud Reconstruction](https://mlsanity.com/paper/2503.18527/) (2025)

## Abstract (arXiv)

In this paper, we present a novel deep method to reconstruct a point cloud of an object from a single still image. Prior arts in the field struggle to reconstruct an accurate and scalable 3D model due to either the inefficient and expensive 3D representations, the dependency between the output and number of model parameters or the lack of a suitable computing operation. We propose to overcome these by deforming a random point cloud to the object shape through two steps: feature blending and deformation. In the first step, the global and point-specific shape features extracted from a 2D object image are blended with the encoded feature of a randomly generated point cloud, and then this mixture is sent to the deformation step to produce the final representative point set of the object. In the deformation process, we introduce a new layer termed as GraphX that considers the inter-relationship between points like common graph convolutions but operates on unordered sets. Moreover, with a simple trick, the proposed model can generate an arbitrary-sized point cloud, which is the first deep method to do so. Extensive experiments verify that we outperform existing models and halve the state-of-the-art distance score in single image 3D reconstruction.