English
Related papers

Related papers: Learning 3D Dense Correspondence via Canonical Poi…

200 papers

Understanding of spatial attributes is central to effective 3D radiology image analysis where crop-based learning is the de facto standard. Given an image patch, its core spatial properties (e.g., position & orientation) provide helpful…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Yejia Zhang , Nishchal Sapkota , Pengfei Gu , Yaopeng Peng , Hao Zheng , Danny Z. Chen

In computer-aided design (CAD) community, the point cloud data is pervasively applied in reverse engineering, where the point cloud analysis plays an important role. While a large number of supervised learning methods have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Cheng Zhang , Jian Shi , Xuan Deng , Zizhao Wu

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Junyu Chen , Han Cai , Junsong Chen , Enze Xie , Shang Yang , Haotian Tang , Muyang Li , Yao Lu , Song Han

Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly solve dense tasks…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Souhail Hadgi , Bingchen Gong , Ramana Sundararaman , Emery Pierson , Lei Li , Peter Wonka , Maks Ovsjanikov

Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., either images or point…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Ziyu Guo , Renrui Zhang , Longtian Qiu , Xianzhi Li , Pheng-Ann Heng

We present the first utterly self-supervised network for dense correspondence mapping between non-isometric shapes. The task of alignment in non-Euclidean domains is one of the most fundamental and crucial problems in computer vision. As 3D…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Dvir Ginzburg , Dan Raviv

Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation. In this work, a novel end-to-end deep…

Computer Vision and Pattern Recognition · Computer Science 2018-04-04 Yaoqing Yang , Chen Feng , Yiru Shen , Dong Tian

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Di Huang , Sida Peng , Tong He , Honghui Yang , Xiaowei Zhou , Wanli Ouyang

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations? To answer that, we introduce a point cloud…

Computer Vision and Pattern Recognition · Computer Science 2023-05-16 Xiaoyu Tian , Haoxi Ran , Yue Wang , Hang Zhao

In classification problems, supervised machine-learning methods outperform traditional algorithms, thanks to the ability of neural networks to learn complex patterns. However, in two-class classification tasks like anomaly or fraud…

Machine Learning · Computer Science 2022-04-01 Mihai-Cezar Augustin , Vivien Bonvin , Regis Houssou , Efstratios Rappos , Stephan Robert-Nicoud

Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Octave Mariotti , Oisin Mac Aodha , Hakan Bilen

We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations (such as changes in pose) approximately preserve the metric structure…

Computer Vision and Pattern Recognition · Computer Science 2018-12-07 Oshri Halimi , Or Litany , Emanuele Rodolà , Alex Bronstein , Ron Kimmel

We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method…

Computer Vision and Pattern Recognition · Computer Science 2018-07-09 Maxim Tatarchenko , Jaesik Park , Vladlen Koltun , Qian-Yi Zhou

Using 3D point clouds in odometry estimation in robotics often requires finding a set of correspondences between points in subsequent scans. While there are established methods for point clouds of sufficient quality, state-of-the-art still…

Robotics · Computer Science 2025-06-24 Jan Michalczyk , Stephan Weiss , Jan Steinbrener

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Soyeon Yoon , Chang Wook Seo , Hyunjung Shim

Discriminative deep learning approaches have shown impressive results for problems where human-labeled ground truth is plentiful, but what about tasks where labels are difficult or impossible to obtain? This paper tackles one such problem:…

Computer Vision and Pattern Recognition · Computer Science 2016-04-20 Tinghui Zhou , Philipp Krähenbühl , Mathieu Aubry , Qixing Huang , Alexei A. Efros

Unsupervised point cloud shape correspondence aims to obtain dense point-to-point correspondences between point clouds without manually annotated pairs. However, humans and some animals have bilateral symmetry and various orientations,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Jiacheng Deng , Chuxin Wang , Jiahao Lu , Jianfeng He , Tianzhu Zhang , Jiyang Yu , Zhe Zhang

We explore the use of deep neural networks for nonlinear dimensionality reduction in climate applications. We train convolutional autoencoders (CAEs) to encode two temperature field datasets from pre-industrial control runs in the CMIP5…

Atmospheric and Oceanic Physics · Physics 2018-09-06 J. A. Saenz , N. Lubbers , N. M. Urban

In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from…

Machine Learning · Statistics 2017-02-09 Michael Kampffmeyer , Sigurd Løkse , Filippo Maria Bianchi , Robert Jenssen , Lorenzo Livi

This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches focus on either combining a spatial regularizer with…

Computer Vision and Pattern Recognition · Computer Science 2017-08-18 Kai Han , Rafael S. Rezende , Bumsub Ham , Kwan-Yee K. Wong , Minsu Cho , Cordelia Schmid , Jean Ponce