# Dynamic Plane Convolutional Occupancy Networks

arXiv: https://arxiv.org/abs/2011.05813 · HTML: https://mlsanity.com/paper/2011.05813/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 24 of 24)

- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM](https://mlsanity.com/paper/2302.03594/) (2023)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space](https://mlsanity.com/paper/2204.02394/) (2022)
- [ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2212.04096/) (2022)
- [EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting](https://mlsanity.com/paper/2405.14959/) (2024)
- [Unsupervised Occupancy Learning from Sparse Point Cloud](https://mlsanity.com/paper/2404.02759/) (2024)
- [NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping](https://mlsanity.com/paper/2110.09415/) (2021)
- [Mixing-Denoising Generalizable Occupancy Networks](https://mlsanity.com/paper/2311.12125/) (2023)
- [Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model](https://mlsanity.com/paper/2311.12967/) (2023)
- [NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF](https://mlsanity.com/paper/2307.09112/) (2023)
- [GridFormer: Point-Grid Transformer for Surface Reconstruction](https://mlsanity.com/paper/2401.02292/) (2024)
- [DeepMend: Learning Occupancy Functions to Represent Shape for Repair](https://mlsanity.com/paper/2210.05728/) (2022)
- [FastHuman: Reconstructing High-Quality Clothed Human in Minutes](https://mlsanity.com/paper/2211.14485/) (2022)
- [DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair](https://mlsanity.com/paper/2211.12400/) (2022)
- [Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries](https://mlsanity.com/paper/2408.15114/) (2024)
- [Toward Robust Neural Reconstruction from Sparse Point Sets](https://mlsanity.com/paper/2412.16361/) (2024)
- [Projection-based Point Convolution for Efficient Point Cloud Segmentation](https://mlsanity.com/paper/2202.01991/) (2022)
- [Implicit Modeling of Non-rigid Objects with Cross-Category Signals](https://mlsanity.com/paper/2312.10246/) (2023)
- [PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction](https://mlsanity.com/paper/2401.08518/) (2024)
- [Occupancy-Based Dual Contouring](https://mlsanity.com/paper/2409.13418/) (2024)
- [Oriented-grid Encoder for 3D Implicit Representations](https://mlsanity.com/paper/2402.06752/) (2024)
- [DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2403.05005/) (2024)

## Abstract (arXiv)

Learning-based 3D reconstruction using implicit neural representations has shown promising progress not only at the object level but also in more complicated scenes. In this paper, we propose Dynamic Plane Convolutional Occupancy Networks, a novel implicit representation pushing further the quality of 3D surface reconstruction. The input noisy point clouds are encoded into per-point features that are projected onto multiple 2D dynamic planes. A fully-connected network learns to predict plane parameters that best describe the shapes of objects or scenes. To further exploit translational equivariance, convolutional neural networks are applied to process the plane features. Our method shows superior performance in surface reconstruction from unoriented point clouds in ShapeNet as well as an indoor scene dataset. Moreover, we also provide interesting observations on the distribution of learned dynamic planes.