3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View

• URL: http://arxiv.org/abs/2008.06133v1
• Date: Thu, 13 Aug 2020 23:29:04 GMT
• Title: 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View
• Authors: Marc Badger, Yufu Wang, Adarsh Modh, Ammon Perkes, Nikos Kolotouros, Bernd G. Pfrommer, Marc F. Schmidt, Kostas Daniilidis
• Abstract summary: We introduce a model and multi-view optimization approach to capture the unique shape and pose space displayed by live birds. We then introduce a pipeline and experiments for keypoint, mask, pose, and shape regression that recovers accurate avian postures from single views. We provide extensive multi-view keypoint and mask annotations collected from a group of 15 social birds housed together in an outdoor aviary.
• Score: 35.61330221535231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated capture of animal pose is transforming how we study neuroscience and social behavior. Movements carry important social cues, but current methods are not able to robustly estimate pose and shape of animals, particularly for social animals such as birds, which are often occluded by each other and objects in the environment. To address this problem, we first introduce a model and multi-view optimization approach, which we use to capture the unique shape and pose space displayed by live birds. We then introduce a pipeline and experiments for keypoint, mask, pose, and shape regression that recovers accurate avian postures from single views. Finally, we provide extensive multi-view keypoint and mask annotations collected from a group of 15 social birds housed together in an outdoor aviary. The project website with videos, results, code, mesh model, and the Penn Aviary Dataset can be found at https://marcbadger.github.io/avian-mesh.

Related papers

• Context-Aware Outlier Rejection for Robust Multi-View 3D Tracking of Similar Small Birds in An Outdoor Aviary [39.35431651202991]
  This paper presents a novel approach for robust 3D tracking of multiple birds in an outdoor aviary using a multi-camera system. Our method addresses the challenges of visually similar birds and their rapid movements by leveraging environmental landmarks for enhanced feature matching and 3D reconstruction. We also provide a large annotated dataset of 80 birds residing in four enclosures for 20 hours of footage which provides a rich testbed for researchers in computer vision, ornithologists, and ecologists.
  arXiv  Detail & Related papers  (2024-12-21T07:20:57Z)
• Generative Zoo [41.65977386204797]
  We introduce a pipeline that samples a diverse set of poses and shapes for a variety of mammalian quadrupeds and generates realistic images with corresponding ground-truth pose and shape parameters. We train a 3D pose and shape regressor on GenZoo, which achieves state-of-the-art performance on a real-world animal pose and shape estimation benchmark.
  arXiv  Detail & Related papers  (2024-12-11T04:57:53Z)
• Reconstructing Animals and the Wild [51.98009864071166]
  We propose a method to reconstruct natural scenes from single images. We base our approach on advances leveraging the strong world priors in Large Language Models. We propose a synthetic dataset comprising one million images and thousands of assets.
  arXiv  Detail & Related papers  (2024-11-27T23:24:27Z)
• Temporally-consistent 3D Reconstruction of Birds [5.787285686300833]
  We propose an approach to reconstruct the 3D pose and shape from monocular videos of a specific breed of seabird - the common murre. We provide a real-world dataset of 10000 frames of video observations on average capture nine birds simultaneously.
  arXiv  Detail & Related papers  (2024-08-24T17:12:36Z)
• Learning the 3D Fauna of the Web [70.01196719128912]
  We develop 3D-Fauna, an approach that learns a pan-category deformable 3D animal model for more than 100 animal species jointly. One crucial bottleneck of modeling animals is the limited availability of training data. We show that prior category-specific attempts fail to generalize to rare species with limited training images.
  arXiv  Detail & Related papers  (2024-01-04T18:32:48Z)
• Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviary [32.19504891200443]
  We introduce a system for studying the behavioral dynamics of a group of songbirds as they move throughout a 3D aviary. We study the complexities that arise when tracking a group of closely interacting animals in three dimensions and introduce a novel dataset for evaluating multi-view trackers.
  arXiv  Detail & Related papers  (2022-12-01T04:23:18Z)
• MagicPony: Learning Articulated 3D Animals in the Wild [81.63322697335228]
  We present a new method, dubbed MagicPony, that learns this predictor purely from in-the-wild single-view images of the object category. At its core is an implicit-explicit representation of articulated shape and appearance, combining the strengths of neural fields and meshes.
  arXiv  Detail & Related papers  (2022-11-22T18:59:31Z)
• Learning-based Monocular 3D Reconstruction of Birds: A Contemporary Survey [6.555250822345809]
  In nature, the collective behavior of animals is dominated by the interactions between individuals of the same species. Recent advances in 3D vision have led to a number of impressive works on the 3D shape and pose estimation. This work is the first attempt to provide an overview of recent advances in 3D bird reconstruction based on monocular vision.
  arXiv  Detail & Related papers  (2022-07-10T18:13:25Z)
• Neural Rendering of Humans in Novel View and Pose from Monocular Video [68.37767099240236]
  We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.
  arXiv  Detail & Related papers  (2022-04-04T03:09:20Z)
• Unsupervised Shape and Pose Disentanglement for 3D Meshes [49.431680543840706]
  We present a simple yet effective approach to learn disentangled shape and pose representations in an unsupervised setting. We use a combination of self-consistency and cross-consistency constraints to learn pose and shape space from registered meshes. We demonstrate the usefulness of learned representations through a number of tasks including pose transfer and shape retrieval.
  arXiv  Detail & Related papers  (2020-07-22T11:00:27Z)

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.