ARO-Net: Learning Implicit Fields from Anchored Radial Observations
- URL: http://arxiv.org/abs/2212.10275v2
- Date: Sun, 26 Mar 2023 00:32:35 GMT
- Title: ARO-Net: Learning Implicit Fields from Anchored Radial Observations
- Authors: Yizhi Wang, Zeyu Huang, Ariel Shamir, Hui Huang, Hao Zhang, Ruizhen Hu
- Abstract summary: We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes.
We develop a general and unified shape representation by employing a fixed set of anchors, via Fibonacci sampling, and designing a coordinate-based deep neural network.
We demonstrate the quality and generality of our network, coined ARO-Net, on surface reconstruction from sparse point clouds.
- Score: 25.703496065476067
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We introduce anchored radial observations (ARO), a novel shape encoding for
learning implicit field representation of 3D shapes that is category-agnostic
and generalizable amid significant shape variations. The main idea behind our
work is to reason about shapes through partial observations from a set of
viewpoints, called anchors. We develop a general and unified shape
representation by employing a fixed set of anchors, via Fibonacci sampling, and
designing a coordinate-based deep neural network to predict the occupancy value
of a query point in space. Differently from prior neural implicit models that
use global shape feature, our shape encoder operates on contextual,
query-specific features. To predict point occupancy, locally observed shape
information from the perspective of the anchors surrounding the input query
point are encoded and aggregated through an attention module, before implicit
decoding is performed. We demonstrate the quality and generality of our
network, coined ARO-Net, on surface reconstruction from sparse point clouds,
with tests on novel and unseen object categories, "one-shape" training, and
comparisons to state-of-the-art neural and classical methods for reconstruction
and tessellation.
Related papers
- Unsupervised Non-Rigid Point Cloud Matching through Large Vision Models [1.3030624795284795]
We propose a learning-based framework for non-rigid point cloud matching.
Key insight is to incorporate semantic features derived from large vision models (LVMs)
Our framework effectively leverages the structural information contained in the semantic features to address ambiguities arise from self-similarities among local geometries.
arXiv Detail & Related papers (2024-08-16T07:02:19Z) - Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries.
We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images.
Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
arXiv Detail & Related papers (2024-07-26T06:29:09Z) - Shape Anchor Guided Holistic Indoor Scene Understanding [9.463220988312218]
We propose a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding.
AncLearn generates anchors that dynamically fit instance surfaces to (i) unmix noise and target-related features for offering reliable proposals at the detection stage.
We embed AncLearn into a reconstruction-from-detection learning system (AncRec) to generate high-quality semantic scene models.
arXiv Detail & Related papers (2023-09-20T08:30:20Z) - 3D Object Classification on Partial Point Clouds: A Practical
Perspective [91.81377258830703]
A point cloud is a popular shape representation adopted in 3D object classification.
This paper introduces a practical setting to classify partial point clouds of object instances under any poses.
A novel algorithm in an alignment-classification manner is proposed in this paper.
arXiv Detail & Related papers (2020-12-18T04:00:56Z) - 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) - Deep Positional and Relational Feature Learning for Rotation-Invariant
Point Cloud Analysis [107.9979381402172]
We propose a rotation-invariant deep network for point clouds analysis.
The network is hierarchical and relies on two modules: a positional feature embedding block and a relational feature embedding block.
Experiments show state-of-the-art classification and segmentation performances on benchmark datasets.
arXiv Detail & Related papers (2020-11-18T04:16:51Z) - Refinement of Predicted Missing Parts Enhance Point Cloud Completion [62.997667081978825]
Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape.
Previous approaches propose neural networks to directly estimate the whole point cloud through encoder-decoder models fed by the incomplete point set.
This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud.
arXiv Detail & Related papers (2020-10-08T22:01:23Z) - Shape-Oriented Convolution Neural Network for Point Cloud Analysis [59.405388577930616]
Point cloud is a principal data structure adopted for 3D geometric information encoding.
Shape-oriented message passing scheme dubbed ShapeConv is proposed to focus on the representation learning of the underlying shape formed by each local neighboring point.
arXiv Detail & Related papers (2020-04-20T16:11:51Z) - A Rotation-Invariant Framework for Deep Point Cloud Analysis [132.91915346157018]
We introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs.
Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure.
We evaluate our method on multiple point cloud analysis tasks, including shape classification, part segmentation, and shape retrieval.
arXiv Detail & Related papers (2020-03-16T14:04:45Z)
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.