Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models

• URL: http://arxiv.org/abs/2412.18605v1
• Date: Tue, 24 Dec 2024 18:58:43 GMT
• Title: Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
• Authors: Zehan Wang, Ziang Zhang, Tianyu Pang, Chao Du, Hengshuang Zhao, Zhou Zhao,
• Abstract summary: Orient Anything is the first expert and foundational model designed to estimate object orientation in a single image. By developing a pipeline to annotate the front face of 3D objects, we collect 2M images with precise orientation annotations. Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images.
• Score: 79.96917782423219
• License:
• Abstract: Orientation is a key attribute of objects, crucial for understanding their spatial pose and arrangement in images. However, practical solutions for accurate orientation estimation from a single image remain underexplored. In this work, we introduce Orient Anything, the first expert and foundational model designed to estimate object orientation in a single- and free-view image. Due to the scarcity of labeled data, we propose extracting knowledge from the 3D world. By developing a pipeline to annotate the front face of 3D objects and render images from random views, we collect 2M images with precise orientation annotations. To fully leverage the dataset, we design a robust training objective that models the 3D orientation as probability distributions of three angles and predicts the object orientation by fitting these distributions. Besides, we employ several strategies to improve synthetic-to-real transfer. Our model achieves state-of-the-art orientation estimation accuracy in both rendered and real images and exhibits impressive zero-shot ability in various scenarios. More importantly, our model enhances many applications, such as comprehension and generation of complex spatial concepts and 3D object pose adjustment.

Related papers

• FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views [93.6881532277553]
  We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes.
  arXiv  Detail & Related papers  (2025-02-17T18:54:05Z)
• UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
  UPose3D is a novel approach for multi-view 3D human pose estimation. It improves robustness and flexibility without requiring direct 3D annotations.
  arXiv  Detail & Related papers  (2024-04-23T00:18:00Z)
• Learning 3D-Aware GANs from Unposed Images with Template Feature Field [33.32761749864555]
  This work targets learning 3D-aware GANs from unposed images. We propose to perform on-the-fly pose estimation of training images with a learned template feature field (TeFF)
  arXiv  Detail & Related papers  (2024-04-08T17:42:08Z)
• OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation [56.028185293563325]
  This paper studies a new open-set problem, the open-vocabulary category-level object pose and size estimation. We first introduce OO3D-9D, a large-scale photorealistic dataset for this task. We then propose a framework built on pre-trained DinoV2 and text-to-image stable diffusion models.
  arXiv  Detail & Related papers  (2024-03-19T03:09:24Z)
• LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot grasping [9.690844449175948]
  We focus on object pose estimation. Our approach relies on three pieces of information: multiple views of the object, the camera's parameters at those viewpoints, and 3D CAD models of objects. We show that the estimated object pose results in 99.65% grasp accuracy with the ground truth grasp candidates.
  arXiv  Detail & Related papers  (2023-11-14T14:27:53Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)
• Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose [10.028521796737314]
  We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D pose annotation from the labelled to unlabelled images reliably.
  arXiv  Detail & Related papers  (2021-10-27T06:53:53Z)
• Sparse Pose Trajectory Completion [87.31270669154452]
  We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views. This is achieved with a cross-modal pose trajectory transfer mechanism. Our method is evaluated on the Pix3D and ShapeNet datasets.
  arXiv  Detail & Related papers  (2021-05-01T00:07:21Z)
• Novel Object Viewpoint Estimation through Reconstruction Alignment [45.16865218423492]
  We learn a reconstruct and align approach to estimate the viewpoint of a novel object. In particular, we propose learning two networks: the first maps images to a 3D geometry-aware feature bottleneck and is trained via an image-to-image translation loss. At test time, our model finds the relative transformation that best aligns the bottleneck features of our test image to a reference image.
  arXiv  Detail & Related papers  (2020-06-05T17:58:14Z)

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.