Discovering Relationships between Object Categories via Universal Canonical Maps

• URL: http://arxiv.org/abs/2106.09758v1
• Date: Thu, 17 Jun 2021 18:38:18 GMT
• Title: Discovering Relationships between Object Categories via Universal Canonical Maps
• Authors: Natalia Neverova, Artsiom Sanakoyeu, Patrick Labatut, David Novotny, Andrea Vedaldi
• Abstract summary: We tackle the problem of learning the geometry of multiple categories of deformable objects jointly. Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects. We show that improved correspondences can be learned automatically as a natural byproduct of learning category-specific dense pose predictors.
• Score: 80.07703460198198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We tackle the problem of learning the geometry of multiple categories of deformable objects jointly. Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects. However, training such models requires to initialize inter-category correspondences by hand. This is suboptimal and the resulting models fail to maintain correct correspondences as individual categories are learned. In this paper, we show that improved correspondences can be learned automatically as a natural byproduct of learning category-specific dense pose predictors. To do this, we express correspondences between different categories and between images and categories using a unified embedding. Then, we use the latter to enforce two constraints: symmetric inter-category cycle consistency and a new asymmetric image-to-category cycle consistency. Without any manual annotations for the inter-category correspondences, we obtain state-of-the-art alignment results, outperforming dedicated methods for matching 3D shapes. Moreover, the new model is also better at the task of dense pose prediction than prior work.

Related papers

• Learning Correspondence for Deformable Objects [3.5183793234085927]
  We investigate pixelwise correspondence for deformable objects, namely cloth and rope, by comparing both classical and learning-based methods. We present an exhaustive survey of existing classical methods for doing correspondence via feature-matching, including SIFT, SURF, and ORB, and two recently published learning-based methods including TimeCycle and Dense Object Nets. Our proposed method provides a flexible, general formulation for learning temporally and spatially continuous correspondences for nonrigid (and rigid) objects.
  arXiv  Detail & Related papers  (2024-05-14T23:41:24Z)
• Prototype-based Embedding Network for Scene Graph Generation [105.97836135784794]
  Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. Due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category. Prototype-based Embedding Network (PE-Net) models entities/predicates with prototype-aligned compact and distinctive representations. PL is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching.
  arXiv  Detail & Related papers  (2023-03-13T13:30:59Z)
• G-MSM: Unsupervised Multi-Shape Matching with Graph-based Affinity Priors [52.646396621449]
  G-MSM is a novel unsupervised learning approach for non-rigid shape correspondence. We construct an affinity graph on a given set of training shapes in a self-supervised manner. We demonstrate state-of-the-art performance on several recent shape correspondence benchmarks.
  arXiv  Detail & Related papers  (2022-12-06T12:09:24Z)
• Fully Convolutional Geometric Features for Category-level Object Alignment [12.741811850885309]
  This paper focuses on pose registration of different object instances from the same category. Our approach transforms instances of the same category to a normalized canonical coordinate frame and uses metric learning to train fully convolutional geometric features.
  arXiv  Detail & Related papers  (2021-03-08T00:31:56Z)
• Isometric Multi-Shape Matching [50.86135294068138]
  Finding correspondences between shapes is a fundamental problem in computer vision and graphics. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis.
  arXiv  Detail & Related papers  (2020-12-04T15:58:34Z)
• Continuous Surface Embeddings [76.86259029442624]
  We focus on the task of learning and representing dense correspondences in deformable object categories. We propose a new, learnable image-based representation of dense correspondences. We demonstrate that the proposed approach performs on par or better than the state-of-the-art methods for dense pose estimation for humans.
  arXiv  Detail & Related papers  (2020-11-24T22:52:15Z)
• Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation [71.59275788106622]
  We propose to learn the underlying class-agnostic commonalities that can be generalized from mask-annotated categories to novel categories. Our model significantly outperforms the state-of-the-art methods on both partially supervised setting and few-shot setting for instance segmentation on COCO dataset.
  arXiv  Detail & Related papers  (2020-07-24T07:23:44Z)

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.