SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space

Chatzipantazis, Evangelos; Stefanos, Pertigkiozoglou,; Dobriban, Edgar; Daniilidis, Kostas

doi:10.48550/arxiv.2204.02394

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, equivariant networks with SE(3)-equivariance are developed to process 3D data such as point clouds [10], meshes [13], and voxels [35]. However, due to the added complexity, most equivariant networks for 3D perception are restricted to relatively simple tasks with small-scale inputs, such as object-wise classification, registration, part segmentation, and reconstruction [30,46,9]. In the following, we will review recent progress in extending equivariance to large-scale outdoor 3D perception tasks.…”

Section: Equivariant Learningmentioning

confidence: 99%

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

Zhu¹,

Han²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we develop rotation-equivariant neural networks for 4D panoptic segmentation. 4D panoptic segmentation is a recently established benchmark task for autonomous driving, which requires recognizing semantic classes and object instances on the road based on LiDAR scans, as well as assigning temporally consistent IDs to instances across time. We observe that the driving scenario is symmetric to rotations on the ground plane. Therefore, rotation-equivariance could provide better generalization and more robust feature learning. Specifically, we review the object instance clustering strategies, and restate the centerness-based approach and the offset-based approach as the prediction of invariant scalar fields and equivariant vector fields. Other sub-tasks are also unified from this perspective, and different invariant and equivariant layers are designed to facilitate their predictions. Through evaluation on the standard 4D panoptic segmentation benchmark of SemanticKITTI, we show that our equivariant models achieve higher accuracy with lower computational costs compared to their non-equivariant counterparts. Moreover, our method sets the new state-of-the-art performance and achieves 1st place on the SemanticKITTI 4D Panoptic Segmentation leaderboard.

show abstract

Section: Equivariant Learningmentioning

confidence: 99%

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

Zhu¹,

Han²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…c) Equivariant neural networks: Chatzipantazis et al [203] introduced an SE(3)-equivariant coordinate-based attention network called TF-ONet for 3-D surface reconstruction. Local shape modeling and equivariance are the two core design principles of this method.…”

Section: ) Implicit Neural Representation Based On Variants Of Sdf Or...mentioning

confidence: 99%

Deep-Learning-Based 3-D Surface Reconstruction—A Survey

Farshian,

Götz,

Cavallaro

et al. 2023

Proc. IEEE

View full text Add to dashboard Cite

In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy

show abstract

SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space

Cited by 2 publications

References 0 publications

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

Deep-Learning-Based 3-D Surface Reconstruction—A Survey

Contact Info

Product

Resources

About