3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction

• URL: http://arxiv.org/abs/2411.00543v2
• Date: Mon, 04 Nov 2024 10:21:57 GMT
• Title: 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
• Authors: Jongmin Lee, Minsu Cho,
• Abstract summary: Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
• Score: 50.07071392673984
• License:
• Abstract: Determining the 3D orientations of an object in an image, known as single-image pose estimation, is a crucial task in 3D vision applications. Existing methods typically learn 3D rotations parametrized in the spatial domain using Euler angles or quaternions, but these representations often introduce discontinuities and singularities. SO(3)-equivariant networks enable the structured capture of pose patterns with data-efficient learning, but the parametrizations in spatial domain are incompatible with their architecture, particularly spherical CNNs, which operate in the frequency domain to enhance computational efficiency. To overcome these issues, we propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression, aligning with the operations of spherical CNNs. Our SO(3)-equivariant pose harmonics predictor overcomes the limitations of spatial parameterizations, ensuring consistent pose estimation under arbitrary rotations. Trained with a frequency-domain regression loss, our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+, with significant improvements in accuracy, robustness, and data efficiency.

Related papers

• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis [11.236094544193605]
  Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities. We propose a real-time RGB-D SLAM system that incorporates a novel view synthesis technique, 3D Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-08-10T21:23:08Z)
• Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation [36.93661496405653]
  We take a global approach to exploit Transformer-temporal information with a concise Graph and Skipped Transformer architecture. Specifically, in 3D pose stage, coarse-grained body parts are deployed to construct a fully data-driven adaptive model. Experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T10:42:09Z)
• Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation [18.011044932979143]
  3DUDA is a method capable of adapting to a nuisance-ridden target domain without 3D or depth data. We represent object categories as simple cuboid meshes, and harness a generative model of neural feature activations. We show that our method simulates fine-tuning on a global pseudo-labeled dataset under mild assumptions.
  arXiv  Detail & Related papers  (2024-01-19T17:48:05Z)
• SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation [66.16525145765604]
  We introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud. Experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets.
  arXiv  Detail & Related papers  (2023-10-26T12:47:26Z)
• Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization [81.29406957201458]
  Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection. We propose to model the rotated objects as Gaussian distributions. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
  arXiv  Detail & Related papers  (2022-09-22T07:50:48Z)
• RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization [46.144194562841435]
  We propose a framework based on a recurrent neural network (RNN) for object pose refinement. The problem is formulated as a non-linear least squares problem based on the estimated correspondence field. The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover accurate object poses.
  arXiv  Detail & Related papers  (2022-03-24T06:24:55Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)

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.