Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases

• URL: http://arxiv.org/abs/2111.06838v1
• Date: Fri, 12 Nov 2021 17:48:25 GMT
• Title: Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases
• Authors: Jan Bednarik, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Shaifali Parashar, Mathieu Salzmann, Pascal Fua
• Abstract summary: We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. Our approach outperforms state-of-the-art ones on several challenging datasets.
• Score: 131.50372468579067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. The key to making these correspondences semantically meaningful is to guarantee that the metric tensors computed at corresponding points are as similar as possible. We have devised an optimization strategy that makes our method robust to noise and global motions, without a priori correspondences or pre-alignment steps. As a result, our approach outperforms state-of-the-art ones on several challenging datasets. The code is available at https://github.com/bednarikjan/temporally_coherent_surface_reconstruction.

Related papers

• Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition [16.380948630155476]
  Visual Place Recognition (VPR) aims to retrieve frames from atagged database that are located at the same place as the query frame. To improve the robustness of VPR in geoly aliasing scenarios, sequence-based VPR methods are proposed. We use a sliding window to control the temporal range of attention and use relative positional encoding to construct sequential relationships between different features.
  arXiv  Detail & Related papers  (2023-05-19T06:39:10Z)
• Data-driven abstractions via adaptive refinements and a Kantorovich metric [extended version] [56.94699829208978]
  We introduce an adaptive refinement procedure for smart, and scalable abstraction of dynamical systems. In order to learn the optimal structure, we define a Kantorovich-inspired metric between Markov chains. We show that our method yields a much better computational complexity than using classical linear programming techniques.
  arXiv  Detail & Related papers  (2023-03-30T11:26:40Z)
• Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization [105.14877281665011]
  We present SyNoRiM, a novel way to register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds. We demonstrate via extensive experiments that our method achieves a state-of-the-art performance in registration accuracy.
  arXiv  Detail & Related papers  (2021-11-25T02:37:59Z)
• Learning Canonical Embedding for Non-rigid Shape Matching [36.85782408336389]
  This paper provides a novel framework that learns canonical embeddings for non-rigid shape matching. Our framework is trained end-to-end and thus avoids instabilities and constraints associated with the commonly-used Laplace-Beltrami basis.
  arXiv  Detail & Related papers  (2021-10-06T18:09:13Z)
• Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases [131.50372468579067]
  We represent the reconstructed surface as an atlas, using a neural network. We empirically show that our method achieves results that exceed that state of the art in the accuracy of unsupervised correspondences and accuracy of surface reconstruction.
  arXiv  Detail & Related papers  (2021-04-14T16:21:22Z)
• Space-Time Correspondence as a Contrastive Random Walk [47.40711876423659]
  We cast correspondence as prediction of links in a space-time graph constructed from video. We learn a representation in which pairwise similarity defines transition probability of a random walk. We demonstrate that a technique we call edge dropout, as well as self-supervised adaptation at test-time, further improve transfer for object-centric correspondence.
  arXiv  Detail & Related papers  (2020-06-25T17:56:05Z)
• FKAConv: Feature-Kernel Alignment for Point Cloud Convolution [75.85619090748939]
  We provide a formulation to relate and analyze a number of point convolution methods. We also propose our own convolution variant, that separates the estimation of geometry-less kernel weights. We show competitive results on classification and semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2020-04-09T10:12:45Z)
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation [67.47159595239798]
  We apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. We achieve comparable performance with advantages in computational and memory overhead.
  arXiv  Detail & Related papers  (2020-03-23T12:28:07Z)
• Deep Graph Matching Consensus [19.94426142777885]
  This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs.
  arXiv  Detail & Related papers  (2020-01-27T08:05:57Z)

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.