English
Related papers

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

200 papers

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Heng Wang , Chaoyi Zhang , Jianhui Yu , Weidong Cai

In our previous work, we proposed a discriminative autoencoder (DcAE) for speech recognition. DcAE combines two training schemes into one. First, since DcAE aims to learn encoder-decoder mappings, the squared error between the reconstructed…

Sound · Computer Science 2022-06-16 Hung-Shin Lee , Pin-Tuan Huang , Yao-Fei Cheng , Hsin-Min Wang

Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not…

Machine Learning · Statistics 2019-12-03 Adam R. Kosiorek , Sara Sabour , Yee Whye Teh , Geoffrey E. Hinton

Defining and reliably finding a canonical orientation for 3D surfaces is key to many Computer Vision and Robotics applications. This task is commonly addressed by handcrafted algorithms exploiting geometric cues deemed as distinctive and…

Computer Vision and Pattern Recognition · Computer Science 2020-11-16 Riccardo Spezialetti , Federico Stella , Marlon Marcon , Luciano Silva , Samuele Salti , Luigi Di Stefano

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in…

Computer Vision and Pattern Recognition · Computer Science 2017-06-22 Chen-Hsuan Lin , Chen Kong , Simon Lucey

We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use…

Computer Vision and Pattern Recognition · Computer Science 2020-02-19 Siheng Chen , Chaojing Duan , Yaoqing Yang , Duanshun Li , Chen Feng , Dong Tian

We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a…

Machine Learning · Computer Science 2019-12-10 Nitish Srivastava , Hanlin Goh , Ruslan Salakhutdinov

Existing 3D foundation models typically align point clouds to frozen vision-language spaces like CLIP, which achieve strong cross-modal retrieval by compressing 3D shape into a global vector. However, this global-only alignment cannot…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zebin He , Mingxin Yang , Shuhui Yang , Hanxiao Sun , Xintong Han , Chunchao Guo , Wenhan Luo

We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of randomly rotated…

Computer Vision and Pattern Recognition · Computer Science 2021-11-29 Weiwei Sun , Andrea Tagliasacchi , Boyang Deng , Sara Sabour , Soroosh Yazdani , Geoffrey Hinton , Kwang Moo Yi

This study investigates the direct use of speech waveforms to predict head motion for speech-driven head-motion synthesis, whereas the use of spectral features such as MFCC as basic input features together with additional features such as…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-03 JinHong Lu , Hiroshi Shimodaira

We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant, while…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Oren Katzir , Dani Lischinski , Daniel Cohen-Or

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

Computer Vision and Pattern Recognition · Computer Science 2019-09-30 Mingtao Feng , Liang Zhang , Xuefei Lin , Syed Zulqarnain Gilani , Ajmal Mian

We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects. Our method builds in a novel way on concepts from…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 David Novotny , Roman Shapovalov , Andrea Vedaldi

In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Yulin Wang , Mengting Hu , Hongli Li , Chen Luo

This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds. Despite the recent success achieved by extending deep implicit representations into 4D space, it is still a great challenge in two respects, i.e. how…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Jiapeng Tang , Dan Xu , Kui Jia , Lei Zhang

Masked autoencoders (MAE) have recently been introduced to 3D self-supervised pretraining for point clouds due to their great success in NLP and computer vision. Unlike MAEs used in the image domain, where the pretext task is to restore…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Siming Yan , Yuqi Yang , Yuxiao Guo , Hao Pan , Peng-shuai Wang , Xin Tong , Yang Liu , Qixing Huang

In this paper, we present a deep learning model that exploits the power of self-supervision to perform 3D point cloud completion, estimating the missing part and a context region around it. Local and global information are encoded in a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Antonio Alliegro , Diego Valsesia , Giulia Fracastoro , Enrico Magli , Tatiana Tommasi

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Natalia Neverova , David Novotny , Vasil Khalidov , Marc Szafraniec , Patrick Labatut , Andrea Vedaldi

In recent years, deep neural networks have yielded state-of-the-art performance on several tasks. Although some recent works have focused on combining deep learning with recommendation, we highlight three issues of existing models. First,…

Machine Learning · Computer Science 2018-12-20 Qibing Li , Xiaolin Zheng , Xinyue Wu

Masked autoencoder has demonstrated its effectiveness in self-supervised point cloud learning. Considering that masking is a kind of corruption, in this work we explore a more general denoising autoencoder for point cloud learning…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yabin Zhang , Jiehong Lin , Ruihuang Li , Kui Jia , Lei Zhang