ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching

• URL: http://arxiv.org/abs/2604.25065v1
• Date: Mon, 27 Apr 2026 23:42:52 GMT
• Title: ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching
• Abstract summary: Object recognition in humans relies heavily on shape cues and the ability to recognize objects across varying 3D viewpoints.<n>Unlike humans, deep networks often rely on non-shape cues such as texture and background, leading to vulnerabilities in generalization and robustness.<n>We introduce ShapeY, a novel and principled benchmarking framework designed to evaluate shape-based recognition capability in OR systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Object recognition (OR) in humans relies heavily on shape cues and the ability to recognize objects across varying 3D viewpoints. Unlike humans, deep networks often rely on non-shape cues such as texture and background, leading to vulnerabilities in generalization and robustness. To address this gap, we introduce ShapeY, a novel and principled benchmarking framework designed to evaluate shape-based recognition capability in OR systems. ShapeY comprises 68,200 grayscale images of 200 3D objects rendered from multiple viewpoints and optionally subjected to non-shape ``appearance'' changes. Using a nearest-neighbor matching task, ShapeY specifically probes the fine-grained structure of an OR system's embedding space by evaluating whether object views are clustered by 3D shape similarity across varying 3D viewpoints and other non-shape changes. ShapeY provides a suite of quantitative and qualitative performance readouts, including error rate graphs, viewpoint tuning curves, histograms of positive and negative matching scores, and grids showing ordered best matches, which together offer a comprehensive evaluation of an OR system's shape understanding capability. Testing of 321 pre-trained networks with diverse architectures reveals significant challenges in achieving robust shape-based recognition: even state-of-the-art models struggle to generalize consistently across 3D viewpoint and appearance changes, and are prone to infrequent but egregious matches of objects of obviously completely different shape. ShapeY establishes a principled framework for advancing artificial vision systems toward human-like shape recognition capabilities, emphasizing the importance of disentangled and invariant object encodings.

Related papers

• Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View [69.6117755984012]
  Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision.<n>We propose a unified category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image.
  arXiv  Detail & Related papers  (2025-10-13T17:49:15Z)
• Visual Anagrams Reveal Hidden Differences in Holistic Shape Processing Across Vision Models [4.749824105387293]
  We recast shape evaluation as a matter of absolute configural competence, operationalized by the Configural Shape Score (CSS)<n>CSS uncovers a broad spectrum of configural sensitivity with fully self-supervised and language-aligned transformers.<n>We propose that the path toward truly robust, generalizable, and human-like vision systems may not lie in forcing an artificial choice between shape and texture.
  arXiv  Detail & Related papers  (2025-07-01T07:08:56Z)
• Robust 3D Tracking with Quality-Aware Shape Completion [67.9748164949519]
  We propose a synthetic target representation composed of dense and complete point clouds depicting the target shape precisely by shape completion for robust 3D tracking. Specifically, we design a voxelized 3D tracking framework with shape completion, in which we propose a quality-aware shape completion mechanism to alleviate the adverse effect of noisy historical predictions.
  arXiv  Detail & Related papers  (2023-12-17T04:50:24Z)
• Deformation-Guided Unsupervised Non-Rigid Shape Matching [7.327850781641328]
  We present an unsupervised data-driven approach for non-rigid shape matching. Our approach is particularly robust when matching digitized shapes using 3D scanners.
  arXiv  Detail & Related papers  (2023-11-27T09:55:55Z)
• Generative Category-Level Shape and Pose Estimation with Semantic Primitives [27.692997522812615]
  We propose a novel framework for category-level object shape and pose estimation from a single RGB-D image. To handle the intra-category variation, we adopt a semantic primitive representation that encodes diverse shapes into a unified latent space. We show that the proposed method achieves SOTA pose estimation performance and better generalization in the real-world dataset.
  arXiv  Detail & Related papers  (2022-10-03T17:51:54Z)
• Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
  We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
  arXiv  Detail & Related papers  (2022-04-21T03:42:31Z)
• ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching [0.0]
  We have developed a new approach to measuring the shape recognition performance of a vision system based on nearest neighbor view matching within the system's embedding space. Our performance benchmark, ShapeY, allows for precise control of task difficulty, by enforcing that view matching span a specified degree of 3D viewpoint change and/or appearance change.
  arXiv  Detail & Related papers  (2021-11-16T01:21:54Z)
• Learning Canonical 3D Object Representation for Fine-Grained Recognition [77.33501114409036]
  We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image. We represent an object as a composition of 3D shape and its appearance, while eliminating the effect of camera viewpoint. By incorporating 3D shape and appearance jointly in a deep representation, our method learns the discriminative representation of the object.
  arXiv  Detail & Related papers  (2021-08-10T12:19:34Z)
• From Points to Multi-Object 3D Reconstruction [71.17445805257196]
  We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. A keypoint detector localizes objects as center points and directly predicts all object properties, including 9-DoF bounding boxes and 3D shapes. The presented approach performs lightweight reconstruction in a single-stage, it is real-time capable, fully differentiable and end-to-end trainable.
  arXiv  Detail & Related papers  (2020-12-21T18:52:21Z)
• Diverse Plausible Shape Completions from Ambiguous Depth Images [7.652701739127332]
  PSSNet is a network architecture for generating plausible 3D reconstructions from a single 2.5D depth image. We perform experiments using Shapenet mugs and partially-occluded YCB objects and find that our method performs comparably in datasets with little ambiguity.
  arXiv  Detail & Related papers  (2020-11-18T16:42:51Z)
• Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation [62.618227434286]
  We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image. We propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior.
  arXiv  Detail & Related papers  (2020-07-16T16:45:05Z)

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.