English
Related papers

Related papers: On the Structural Failure of Chamfer Distance in 3…

200 papers

Many theoretical and experimental studies have used heuristic methods to investigate the dynamic behaviour of the passive coupling of adjacent structures. However, few papers have used optimization techniques with guaranteed convergence in…

Optimization and Control · Mathematics 2015-11-09 K. Bigdeli , W. Hare , J. Nutini , S. Tesfamariam

Recent advances in deep learning-based point cloud registration have improved generalization, yet most methods still require retraining or manual parameter tuning for each new environment. In this paper, we identify three key factors…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Minkyun Seo , Hyungtae Lim , Kanghee Lee , Luca Carlone , Jaesik Park

Reconstructing 3D objects from 2D images is both challenging for our brains and machine learning algorithms. To support this spatial reasoning task, contextual information about the overall shape of an object is critical. However, such…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Dominik J. E. Waibel , Scott Atwell , Matthias Meier , Carsten Marr , Bastian Rieck

Fixed-budget nonconvex optimization can fail not because local descent is unstable, but because it is too stable: after reaching a nearby stationary point, an optimizer may spend the remaining evaluations refining an uninformative local…

Machine Learning · Computer Science 2026-05-11 Yi Wang , Chandrajit Bajaj

Parameter sharing has proven to be a parameter-efficient approach. Previous work on Transformers has focused on sharing parameters in different layers, which can improve the performance of models with limited parameters by increasing model…

Machine Learning · Computer Science 2023-06-19 Ye Lin , Mingxuan Wang , Zhexi Zhang , Xiaohui Wang , Tong Xiao , Jingbo Zhu

Recovering point clouds involves the sequential process of sampling and restoration, yet existing methods struggle to effectively leverage both topological and geometric attributes. To address this, we propose an end-to-end architecture…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Kaiyue Zhou , Zelong Tan , Hongxiao Wang , Ya-Li Li , Shengjin Wang

Mesh simplification is the process of reducing the number of vertices, edges and triangles in a three-dimensional (3D) mesh while preserving the overall shape and salient features of the mesh. A popular strategy for this is edge collapse,…

Computational Geometry · Computer Science 2025-12-24 Purva Kulkarni , Aravind Shankara Narayanan

We study the relationship between topological defect formation and ground-state packings in a model of repulsions in external confining potentials. Specifically we consider screened 2D Coulombic repulsions, which conveniently parameterizes…

Soft Condensed Matter · Physics 2021-10-04 Qingyou Meng , Gregory M. Grason

The recent trend in deep learning methods for 3D point cloud understanding is to propose increasingly sophisticated architectures either to better capture 3D geometries or by introducing possibly undesired inductive biases. Moreover, prior…

Computer Vision and Pattern Recognition · Computer Science 2023-07-31 Davide Boscaini , Fabio Poiesi

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance…

Machine Learning · Computer Science 2025-12-24 Sasan Sharifipour , Constantino Álvarez Casado , Manuel Lage Cañellas , Miguel Bordallo López

In this paper we introduce and analyze the learning scenario of \emph{coupled nonlinear dimensionality reduction}, which combines two major steps of machine learning pipeline: projection onto a manifold and subsequent supervised learning.…

Machine Learning · Statistics 2015-11-26 Mehryar Mohri , Afshin Rostamizadeh , Dmitry Storcheus

Designing the topology of three-dimensional structures is a challenging problem due to its memory and time consumption. In this paper, we present a robust and efficient algorithm for solving large-scale 3D topology optimization problems.…

Optimization and Control · Mathematics 2024-03-01 Alfredo Vitorino , Francisco A. M. Gomes

Despite its wide range of applications across various domains, the optimization foundations of deep matrix factorization (DMF) remain largely open. In this work, we aim to fill this gap by conducting a comprehensive study of the loss…

Optimization and Control · Mathematics 2026-05-29 Po Chen , Rujun Jiang , Peng Wang

Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider…

Computer Vision and Pattern Recognition · Computer Science 2018-11-29 Navaneet K L , Priyanka Mandikal , Mayank Agarwal , R. Venkatesh Babu

Deep structured-prediction energy-based models combine the expressive power of learned representations and the ability of embedding knowledge about the task at hand into the system. A common way to learn parameters of such models consists…

Machine Learning · Computer Science 2019-03-01 Aleksandr Shevchenko , Anton Osokin

We formulate a general shape and topology optimization problem in structural optimization by using a phase field approach. This problem is considered in view of well-posedness and we derive optimality conditions. We relate the diffuse…

Optimization and Control · Mathematics 2025-08-06 Luise Blank , Harald Garcke , Claudia Hecht , Christoph Rupprecht

Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Ghadi Nehme , Eamon Whalen , Faez Ahmed

Dropout as a common regularizer to prevent overfitting in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is because Dropout drops features randomly, without considering local…

Machine Learning · Computer Science 2025-06-05 Liyan Chen , Philippos Mordohai , Sergul Aydore

Structural defects within amorphous packings of symmetric particles can be characterized using a machine learning approach that incorporates structure functions of radial distances and angular arrangement. This yields a scalar field,…

Soft Condensed Matter · Physics 2019-03-06 Matt Harrington , Andrea J. Liu , Douglas J. Durian