CORTEXA
← Browse
arxivcs.CV2026-07-10

Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks

Yangting Sun, Zijun Cui, Yufei Zhang

In many real-world systems, including articulated robots and biomechanical models, rotations are defined in joint space and naturally parameterized by Euler angles with bounded ranges. Yet regressing Euler angles remains challenging, as their discontinuities and singularities often destabilize training. In this work, we revisit Euler-angle regression and show that its effectiveness depends critically on the interaction between rotation representation, regression architecture, and domain constraints. We introduce a new framework that combines range-aware Euler modeling with Kolmogorov-Arnold Networks (KAN), which replace fixed node-wise activations with learnable univariate functions on edges. We further provide theoretical analysis indicating that bounded Euler ranges motivate a near-additive structure in the regression function, which favors the additive functional form of KAN, and we confirm this trend empirically. Extensive experiments on controlled rotation regression, object pose estimation, and robotic and human inverse kinematics demonstrate consistent improvements in accuracy, convergence, and efficiency. The code will be publicly available.

View free PDFSource page

Related papers

arxivcs.CV2026-07-11

TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction

Md Mustafizur Rahman, Guangchao Yang, A F M Abdun Noor, Md Imam Ahasan, Md Mahfuzur Rahman, Md Ariful Islam

Accurate pedestrian trajectory prediction in crowded environments remains challenging due to the multimodal uncertainty of human motion and the variable complexity of motion dynamics across different scene contexts. Existing goal-conditioned models rely on static displacement str…

View free PDFSource page
arxivcs.CV2026-06-30

Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak, Byungkon Kang, Francois Rameau

Scene Coordinate Regression (SCR) methods are increasingly adopted for visual localization. In these approaches, the scene is implicitly encoded within a neural network that regresses a 3D world coordinate for each image pixel. Because the scene is represented only through the ne…

View free PDFSource page
arxivcs.CVcs.HC2026-06-29

Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose

Mohammadreza Jamalifard, Yaxiong Lei, Parastoo Azizinezhad, Javier Andreu-Perez

Conformal prediction provides distribution-free reliability guarantees for vision systems, but these guarantees depend on how prediction errors are measured in the output space. Many vision tasks produce outputs on curved spaces (e.g. gaze directions on the sphere or 3D head rota…

View free PDFSource page
arxivcs.CVcs.AIcs.RO2026-07-07

MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices

Parsa Hassani Shariat Panahi, Amir Hossein Jalilvand, M. Hassan Najafi

Line segment detection is a key building block in visual SLAM, 3D reconstruction, and industrial inspection. Recent deep learning methods have greatly improved accuracy, yet even the smallest models require several megabytes of memory, exceeding low-cost MCU capacity. This work i…

View free PDFSource page
arxivcs.CV2026-06-29

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment

Yuan Li, Youyuan Lin, Zitang Sun, Yung-Hao Yang, Kiyofumi Miyoshi, Chenhui Chu, et al.

Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers quality structure from ordinal relations. Although joint regression-ranking supervision often improves…

View free PDFSource page