Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes

• URL: http://arxiv.org/abs/2604.18208v1
• Date: Mon, 20 Apr 2026 12:55:36 GMT
• Title: Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
• Abstract summary: Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities are rarely discussed in the literature.<n>We use our representation, SARR, to obtain canonic (symmetry-resolved) poses for the symmetric objects in two popular 6D pose estimation datasets.<n>Our networks outperform the state of the art using $textAR_textC$ and achieve satisfactory performance when using conventional symmetry-invariant measures.
• Score: 0.45880283710344066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks for pose estimation are rarely discussed in the literature. To cope with these ambiguities, existing solutions typically require the design of specific loss functions and network architectures or resort to symmetry-invariant evaluation metrics. In contrast, we focus on the numeric representation of the rotation itself, modifying trigonometric identities with the degrees of symmetry derived from the objects' shapes. We use our representation, SARR, to obtain canonic (symmetry-resolved) poses for the symmetric objects in two popular 6D pose estimation datasets, T-LESS and ITODD, where SARR is unique and continuous w.r.t. the visual appearance. This allows us to use a standard CNN for 3D orientation estimation whose performance is evaluated with the symmetry-sensitive cosine distance $\text{AR}_{\text{C}}$. Our networks outperform the state of the art using $\text{AR}_{\text{C}}$ and achieve satisfactory performance when using conventional symmetry-invariant measures. Our method does not require any 3D models but only depth, or, as part of an additional experiment, texture-less RGB/grayscale images as input. We also show that networks trained on SARR outperform the same networks trained on rotation matrices, Euler angles, quaternions, standard trigonometrics or the recently popular 6d representation -- even in inference scenarios where no prior knowledge of the objects' symmetry properties is available. Code and a visualization toolkit are available at https://github.com/akriegler/SARR .

Related papers

• From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data [56.41479248637621]
  We introduce a novel 3D representation learning paradigm, namely textbfPRISM, for textbfPre-training.<n>PRISM learns embeddings by textbfRecovering the textbfIntrinsic textbfSurface geodesic textbfMetric.<n> Experiments demonstrate that our approach shows satisfactory accuracy, robustness, and high efficiency in geodesic distance prediction.
  arXiv  Detail & Related papers  (2026-06-01T13:54:26Z)
• ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild [29.918676050874964]
  We present the first framework for detecting 3D-grounded reflectional symmetries from single, in-the-wild RGB images, focusing on architectural landmarks.<n>We introduce two key innovations: (1) a scalable data annotation pipeline to automatically curate a large-scale dataset of architectural symmetries, ArchSym, from SfM reconstructions by leveraging cross-view image matching; and (2) a single-view symmetry detector that accurately localizes symmetries in 3D by parameterizing them as signed distance maps defined relative to predicted scene geometry.
  arXiv  Detail & Related papers  (2026-04-24T04:12:03Z)
• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry [0.6445605125467574]
  We present a training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2.<n>Our work demonstrates how foundation vision models can help in solving complex 3D geometric problems such as symmetry detection.
  arXiv  Detail & Related papers  (2025-05-30T03:09:18Z)
• Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference [65.42565481489132]
  Humans can easily deduce the relative pose of a previously unseen object, without labeling or training, given only a single query-reference image pair.<n>We propose a novel 3D generalizable relative pose estimation method by elaborating 3D/2.5D shape perception with a 2.5D shape from RGB-D reference.<n>Our differentiable takes the 2.5D rotatable mesh textured by the RGB and the semantic maps (obtained by DINOv2 from the RGB input), then renders new RGB and semantic maps under a novel rotated view.
  arXiv  Detail & Related papers  (2024-06-26T16:01:10Z)
• MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images [57.71600854525037]
  We propose a Fuse-Describe-Match strategy for 6D pose estimation from RGB-D images. MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects.
  arXiv  Detail & Related papers  (2024-03-03T14:01:03Z)
• Self-Supervised Image Representation Learning with Geometric Set Consistency [50.12720780102395]
  We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views.
  arXiv  Detail & Related papers  (2022-03-29T08:57:33Z)
• 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)
• Category-Level Metric Scale Object Shape and Pose Estimation [73.92460712829188]
  We propose a framework that jointly estimates a metric scale shape and pose from a single RGB image. We validated our method on both synthetic and real-world datasets to evaluate category-level object pose and shape.
  arXiv  Detail & Related papers  (2021-09-01T12:16:46Z)
• NeRD: Neural 3D Reflection Symmetry Detector [27.626579746101292]
  We present NeRD, a Neural 3D Reflection Symmetry Detector. We first enumerate the symmetry planes with a coarse-to-fine strategy and then find the best ones by building 3D cost volumes. Our experiments show that the symmetry planes detected with our method are significantly more accurate than the planes from direct CNN regression.
  arXiv  Detail & Related papers  (2021-04-19T17:25:51Z)
• Handling Object Symmetries in CNN-based Pose Estimation [7.1577508803778045]
  We investigate the problems that Convolutional Neural Networks (CNN)-based pose estimators have with symmetric objects. In particular, we find that the popular min-over-symmetries approach for creating a symmetry-aware loss tends not to work well with gradient-based optimization. We propose a representation called "closed symmetry loop" (csl) from these insights, where the angle of relevant vectors is multiplied by the symmetry order and then generalize it to 6-DOF.
  arXiv  Detail & Related papers  (2020-11-26T10:10:25Z)
• Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction [79.98689027127855]
  We propose a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects. Our method builds in a novel way on concepts from parametric deformation models, non-parametric 3D reconstruction, and canonical embeddings. It achieves state-of-the-art results in dense 3D reconstruction on public in-the-wild datasets of faces, cars, and birds.
  arXiv  Detail & Related papers  (2020-08-28T15:44:05Z)
• SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images [26.38270361331076]
  We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images.
  arXiv  Detail & Related papers  (2020-08-02T14:10:09Z)
• Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction [32.14605731030579]
  3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. We present a geometry-based end-to-end deep learning framework that first detects the mirror plane of reflection symmetry that commonly exists in man-made objects and then predicts depth maps by finding the intra-image pixel-wise correspondence of the symmetry.
  arXiv  Detail & Related papers  (2020-06-17T17:58:59Z)

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.