arXiv Computer Vision
Shape-Bayes: Bayesian Inference of Structured Shapes under Visual Ambiguity
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 18
PRISM: A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
arXiv:2602. 11467v2 Announce Type: replace Abstract: Understanding how anatomical shapes evolve in response to developmental covariates - and quantifying their spatially varying uncertainties - is critical in healthcare research.
arXiv Computer Vision
Sep 4
TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided Tokenisation
TokenMatch is a transformer-based model that estimates 3D shape correspondences by adaptively tokenising meshes into curvature-guided patches. Trained only on the BeCoS partial-to-partial dataset, it generalises to full-shape matching without retraining, using self‑ and cross‑attention to learn patch‑ and point‑level relations. Evaluated on CP2P, PSMAL, BeCoS, FAUST, SCAPE, and SHREC'19, TokenMatch consistently outperforms existing methods in mean geodesic error and intersection‑over‑union while achieving sub‑second inference speeds.
arXiv Computer Vision
Oct 9
ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching
ShapeY is a benchmarking framework that evaluates shape-based recognition in object recognition systems using 68,200 grayscale images of 200 3D objects rendered from multiple viewpoints, with optional appearance changes. It employs a nearest‑neighbor matching task to probe how well an embedding space clusters views by 3D shape similarity across varying viewpoints and non‑shape alterations, providing quantitative and qualitative performance readouts such as error rates, viewpoint tuning curves, and matching score histograms. Testing 321 pre‑trained networks shows that even state‑of‑the‑art models struggle to generalize robustly across 3D viewpoint and appearance changes, highlighting gaps in current shape recognition capabilities.
arXiv AI
3d ago
BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation
The paper introduces BALD-SAM, a framework that applies Bayesian Active Learning by Disagreement (BALD) to the Segment Anything Model (SAM) for spatial prompt selection. By freezing the large SAM backbone and modeling uncertainty only in a small prediction head, BALD-SAM efficiently identifies the most informative regions for interactive prompting. Evaluated across 16 diverse datasets, it consistently outperforms human and oracle prompting and surpasses one‑shot baselines, especially on thin and complex structures.
Hugging Face Trending Papers
Jul 8
Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluation
3D Morphable Models (3DMMs) remain the standard parametric shape priors for many state-of-the-art 3D face reconstruction algorithms. However, as these models are derived from a finite number of 3D face samples, they inherit the morphological biases of their training data, potentially limiting their generalizability across diverse global populations.
arXiv Computer Vision
Oct 28
UT-HMR: Uncertainty-Guided Temporal Modeling for Robust 3D Human Mesh Recovery
UT‑HMR is a one‑stage monocular 3D human mesh recovery framework that introduces uncertainty‑guided temporal modeling to address ambiguities caused by weak observations such as distance, occlusion, and motion blur. It predicts a Gaussian distribution over SMPL pose with a low‑rank-plus‑diagonal covariance, converting this into joint‑wise precision weights for heteroscedastic supervision while keeping inference deterministic. Temporal early fusion incorporates neighboring‑frame evidence before pose decoding, enabling the model to resolve pose ambiguities and achieve state‑of‑the‑art results on VIP‑HockeyPose‑v2, WorldPose, and competitive performance on 3DPW using a lightweight ViT‑B backbone.