Planar

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 21

All topics

Removing spurious minima for planar features by skip connections
Oct 1, 2026Jakob Paul Zimmermann, Moritz Grillo, Andrei Balakin +1Flat Minima Skip
Freie Universität Berlin · Technische Universität Berlin
quARtet Marker: A 3D-Printable Multi-Tag Fiducial for Robust Near-Frontal Pose Estimation
Oct 1, 2026Araki Wakiuchi, Hikaru Sasaki, Takamitsu MatsubaraCategory-Level Object Pose Estimation Planar
Materials Informatics Initiative, RD Technology and Digital Transformation Center, JSR Corporation, 3-103-9 Tonomachi, Kawasaki-ku, Kawasaki, Kanagawa, Japan, 210-0821. · Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5 Takayama-cho, Ikoma, Nara, Japan, 630-0192.
PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration
Sep 21, 2026Abolfazl Babanazari, Carson Cramer, Tyler Summers +2Point Cloud Registration Homography
Department of Computer Science, Colorado School of Mines. · Department of Mechanical Engineering, University of Texas at Dallas. · U.S. Army Combat Capabilities Development Command, Army Research Laboratory
Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
Sep 1, 2026Yingwen Zhang, Meng Wang, Liqiang He +1Video Coding Video-Language Models
Department of Computer Science, City University of Hong Kong · School of Data Science, Lingnan University
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
Sep 1, 2026Orcun Cetintas, Guillem Brasó, Tim Meinhardt +1Multi-Object Tracking Monocular Video
1NVIDIA · 2Technical University of Munich
Beyond the Plane: Coupling Planar Vehicle Dynamics with Three-Dimensional Road Geometry
Aug 10, 2026Simon Sagmeister, Phillip Pitschi, Nico Haja +1Vehicle Dynamics Road Networks
Technical University of Munich, Germany; School of Engineering & Design, Department of Mobility Systems Engineering, Institute of Automotive Technology · Technical University of Munich, Germany; School of Engineering & Design, Department of Engineering Physics & Computation, Institute of Automatic Control
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
Aug 5, 2026Hung Truong Thanh Nguyen, Hélène Fournier, Piper Jackson +4Human-Ai Collaboration Intelligence
Analytics Everywhere Lab, University of New Brunswick, Canada · National Research Council Canada, Canada · Thompson Rivers University, Canada +2
NISF++: Geometrically-grounded implicit representations of 3D+time cardiac function from 2D short- and long-axis MR views
Aug 1, 2026Nil Stolt-Ansó, Maik Dannecker, Steven Jia +2Cardiac Magnetic Resonance Imaging Echocardiography
Munich Center for Machine Learning, Technical University Munich, Germany · School of Computation, Information and Technology, Technical University Munich, Germany · TUM University Hospital, Technical University Munich, Germany +2
Lifelong Localization in Dynamic Indoor Environments Combining Odometry with Sparse Distance Sampling
Jul 20, 2026Michael M. Bilevich, Tomer Buber, Dan HalperinOdometry Robot Navigation
Blavatnik School of Computer Science and Artificial Intelligence, Tel-Aviv University, Israel.
TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splatting
Jul 18, 2026Shanshan Pan, Jiale Chen, Yilin Liu +1Planar Topology
Guangdong Provincial Key Laboratory of Visual Media and Multidimensional Intelligence, CSSE, Shenzhen University, China · Autodesk Research, UK
Planar-SfM: Camera Pose Estimation via Homography Graph Embeddings
Jun 30, 2026Gabi Pragier, Matan Karklinsky, David Ungarish +1Scale-Ambiguous Epipolar Geometry Planar
Amazon Prime Video Live Events
Learning to Distort: Weakly-Supervised Image Quality Transfer for Prostate DWI Correction
Jun 17, 2026YuCheng Tang, Wen Yan, Alexander Ng +13Prostate Magnetic Resonance Imaging Distortion
UCL Hawkes Institute and Department of Medical Physics and Biomedical Engineering, University College London, UK · Division of Surgery and Interventional Science, University College London, UK · Centre for Medical Imaging, University College London, UK +5
Comparison Patrols on Drifting Orders: Certified Rank Maintenance, Evolving Planar Maxima, and Selection under Drifting Fitness
Jun 12, 2026Faruk Alpay, Levent SariogluUpper Bounds Order
Department of Computer Engineering, Bahçeşehir University, Istanbul, Turkey
A Geometric Framework for Absolute Pose and Velocity Estimation with Event Cameras
Jun 8, 2026Zibin Liu, Shunkun Liang, Banglei Guan +3Category-Level Object Pose Estimation Motion Estimation
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073, China · independent researcher, Beijing 100000, China
FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects
Jun 1, 2026Axel Dawne, Shinkyu ParkRobotic Manipulator Category-Level Object Pose Estimation
King Abdullah University of Science and Technology (KAUST), Saudi Arabia
Higher-Order Flexible Configurations of Planar Parallel Manipulators Constructed by Averaging
May 4, 2026Yudi Zhao, Georg NawratilRobotic Manipulator Planar
Institute of Discrete Mathematics and Geometry & Center for Geometry and Computational Design, TU Wien, Austria
Robotic Desk Organization: A Multi-Primitive Approach to Manipulating Heterogeneous Objects via Environmental Constraints
May 4, 2026Yi Dong, Yangjun Liu, Jinjun Duan +2Real-World Manipulation Tasks Robotic Grasping
Structure-Augmented Standard Plane Detection with Temporal Aggregation in Blind-Sweep Fetal Ultrasound
Apr 22, 2026Keli Niu, He Zhao, Qianhui MenPrenatal Ultrasound Ultrasound
University of Bristol · University of Liverpool
RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation
Aug 26, 2025Siyuan You, Guozheng Xu, Pengwei Zhou +3Light Detection And Ranging Point Clouds Interactive 3D Segmentation
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China · School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China · Wuhan Unversity Shenzhen Research Institute, Shenzhen 518057, China.
Design optimization and robustness analysis of rigid-link flapping mechanisms
Mar 27, 2025Shyam Sunder Nishad, Anupam SaxenaRotorcraft Kinematic Chain
Department of Mechanical Engineering, IIT Kanpur, India 208016.
Image Matching Filtering and Refinement by Planes and Beyond
Nov 14, 2024Fabio Bellavia, Zhenjun Zhao, Luca Morelli +1Computer Vision Planar
University of Palermo, Italy · University of Zaragoza, Spain · Bruno Kessler Foundation, Italy

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Removing spurious minima for planar features by skip connections

Jakob Paul Zimmermann, Moritz Grillo, Andrei Balakin, Georg Loho

Freie Universität Berlin · Technische Universität Berlin

Flat Minima Skip Model Weights Neurons Planar Removal

Open paper AskPDF arXiv

Understanding loss landscapes is central to explaining neural-network training, yet their structure remains only partially understood even in simple models. We study the Gaussian population loss of shallow, bias-free ReLU networks in the teacher--student setting. This provides a simple model for studying essential aspects such as feature learning and overparameterization. For teacher networks with positive output weights and planar features, we show that including a learned linear skip removes all spurious local minima with non-negative student output weights once the student network is at least as wide as the teacher network. In contrast, without the skip, we construct a fixed teacher network with positive output weights and only three hidden neurons in input dimension two whose spurious local minima persist at every student width at least three. Thus, a learned linear skip can remove spurious minima that persist under arbitrary overparameterization. Furthermore, we show that a positive output weight student network always learns the subspace spanned by the teacher features: student features at local minima with non-negative student output weights lie in the span of the teacher features. For ReLU networks in two dimensions, even heavily overparameterized student networks have effective width controlled by the teacher width: every critical point with positive student output weights has at most twice as many distinct student feature directions as teacher neurons. Finally, we transfer the benignity result to empirical minima over parameter balls of any prescribed radius, with the required sampling accuracy depending on that radius.

Momentum

Related topics

Latest papers 21