Dynamic Plane Convolutional Occupancy Networks
- URL: http://arxiv.org/abs/2011.05813v1
- Date: Wed, 11 Nov 2020 14:24:52 GMT
- Title: Dynamic Plane Convolutional Occupancy Networks
- Authors: Stefan Lionar, Daniil Emtsev, Dusan Svilarkovic, Songyou Peng
- Abstract summary: We propose Dynamic Plane Convolutional Occupancy Networks to push further the quality of 3D surface reconstruction.
A fully-connected network learns to predict plane parameters that best describe the shapes of objects or scenes.
Our method shows superior performance in surface reconstruction from unoriented point clouds in ShapeNet as well as an indoor scene dataset.
- Score: 4.607145155913717
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction [26.39519157164198]
We present DaRePlane, a novel representation approach that captures dynamics from six different directions.
DaRePlane yields state-of-the-art performance in novel view synthesis for various complex dynamic scenes.
arXiv Detail & Related papers (2024-10-18T04:19:10Z) - Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering [57.895846642868904]
We present a 3D generative model named DynaVol-S for dynamic scenes that enables object-centric learning.
voxelization infers per-object occupancy probabilities at individual spatial locations.
Our approach integrates 2D semantic features to create 3D semantic grids, representing the scene through multiple disentangled voxel grids.
arXiv Detail & Related papers (2024-07-30T15:33:58Z) - Object Dynamics Modeling with Hierarchical Point Cloud-based Representations [1.3934784414106087]
We propose a novel U-net architecture based on continuous point convolution which embeds information from 3D coordinates.
Bottleneck layers in the downsampled point clouds lead to better long-range interaction modeling.
Our approach significantly improves the state-of-the-art, especially in scenarios that require accurate gravity or collision reasoning.
arXiv Detail & Related papers (2024-04-09T06:10:15Z) - Dynamic 3D Point Cloud Sequences as 2D Videos [81.46246338686478]
3D point cloud sequences serve as one of the most common and practical representation modalities of real-world environments.
We propose a novel generic representation called textitStructured Point Cloud Videos (SPCVs)
SPCVs re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points.
arXiv Detail & Related papers (2024-03-02T08:18:57Z) - Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud
Analysis [66.49788145564004]
We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology.
Our methods perform favorably against the current state-of-the-art competitors.
arXiv Detail & Related papers (2022-12-17T15:05:25Z) - RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction [19.535169371240073]
We introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from point clouds.
We decouple the instance reconstruction into global object localization and local shape prediction.
Our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.
arXiv Detail & Related papers (2020-11-30T12:58:05Z) - Learning Occupancy Function from Point Clouds for Surface Reconstruction [6.85316573653194]
Implicit function based surface reconstruction has been studied for a long time to recover 3D shapes from point clouds sampled from surfaces.
This paper proposes a novel method for learning occupancy functions from sparse point clouds and achieves better performance on challenging surface reconstruction tasks.
arXiv Detail & Related papers (2020-10-22T02:07:29Z) - Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images [64.53227129573293]
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
We design neural networks capable of generating high-quality parametric 3D surfaces which are consistent between views.
Our method is supervised and trained on a public dataset of shapes from common object categories.
arXiv Detail & Related papers (2020-08-18T06:33:40Z) - KAPLAN: A 3D Point Descriptor for Shape Completion [80.15764700137383]
KAPLAN is a 3D point descriptor that aggregates local shape information via a series of 2D convolutions.
In each of those planes, point properties like normals or point-to-plane distances are aggregated into a 2D grid and abstracted into a feature representation with an efficient 2D convolutional encoder.
Experiments on public datasets show that KAPLAN achieves state-of-the-art performance for 3D shape completion.
arXiv Detail & Related papers (2020-07-31T21:56:08Z) - Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
Representation learning for 3D meshes is important in many computer vision and graphics applications.
We propose a local structure-aware anisotropic convolutional operation (LSA-Conv)
Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
arXiv Detail & Related papers (2020-04-21T13:40:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.