English
Related papers

Related papers: $S^3$: Learnable Sparse Signal Superdensity for Gu…

200 papers

Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Yangchao Wu , Tian Yu Liu , Hyoungseob Park , Stefano Soatto , Dong Lao , Alex Wong

We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of encoding all signals into a fixed embedding, S3 decomposes multimodal inputs into semantic…

Machine Learning · Computer Science 2026-05-07 Hahyeon Choi , Nojun Kwak

Topological data analysis (TDA) has emerged as one of the most promising techniques to reconstruct the unknown shapes of high-dimensional spaces from observed data samples. TDA, thus, yields key shape descriptors in the form of persistent…

Machine Learning · Statistics 2017-11-15 Wei Guo , Krithika Manohar , Steven L. Brunton , Ashis G. Banerjee

Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Samarth Sinha , Jason Y. Zhang , Andrea Tagliasacchi , Igor Gilitschenski , David B. Lindell

Super-symmetric tensors - a higher-order extension of scatter matrices - are becoming increasingly popular in machine learning and computer vision for modelling data statistics, co-occurrences, or even as visual descriptors. However, the…

Computer Vision and Pattern Recognition · Computer Science 2015-09-11 Piotr Koniusz , Anoop Cherian

Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in autonomous driving due to absence of explicit depth cues in a single RGB image. In this paper, we strive to boost currently underperforming monocular…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Weijia Zhang , Dongnan Liu , Chao Ma , Weidong Cai

Millimeter wave multiple-input multiple-output (MIMO) communication systems must operate over sparse wireless links and will require large antenna arrays to provide high throughput. To achieve sufficient array gains, these systems must…

Signal Processing · Electrical Eng. & Systems 2019-04-17 Wei Zhang , Taejoon Kim , David J. Love

Lidar became an important component of the perception systems in autonomous driving. But challenges of training data acquisition and annotation made emphasized the role of the sensor to sensor domain adaptation. In this work, we address the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Artem Savkin , Yida Wang , Sebastian Wirkert , Nassir Navab , Federico Tombar

Monocular Depth Estimation (MDE) is a fundamental problem in computer vision with numerous applications. Recently, LIDAR-supervised methods have achieved remarkable per-pixel depth accuracy in outdoor scenes. However, significant errors are…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Lior Talker , Aviad Cohen , Erez Yosef , Alexandra Dana , Michael Dinerstein

We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images. We take the advantage of the high accuracy of LiDAR to resolve the lack of information in some regions of…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Ramy Battrawy , René Schuster , Oliver Wasenmüller , Qing Rao , Didier Stricker

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also…

Computer Vision and Pattern Recognition · Computer Science 2021-07-15 Jamie Watson , Oisin Mac Aodha , Victor Prisacariu , Gabriel Brostow , Michael Firman

Narrowband and broadband indoor radar images significantly deteriorate in the presence of target dependent and independent static and dynamic clutter arising from walls. A stacked and sparse denoising autoencoder (StackedSDAE) is proposed…

Signal Processing · Electrical Eng. & Systems 2022-01-21 Shobha Sundar Ram , Shelly Vishwakarma , Akanksha Sneh , Kainat Yasmeen

Active stereo systems are used in many robotic applications that require 3D information. These depth sensors, however, suffer from stereo artefacts and do not provide dense depth estimates.In this work, we present the first self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2022-01-21 Frederik Warburg , Daniel Hernandez-Juarez , Juan Tarrio , Alexander Vakhitov , Ujwal Bonde , Pablo F. Alcantarilla

LiDAR-based SLAM algorithms are extensively studied to providing robust and accurate positioning for autonomous driving vehicles (ADV) in the past decades. Satisfactory performance can be obtained using high-grade 3D LiDAR with 64 channels,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Jiang Yue , Weisong Wen , Jing Han , Li-Ta Hsu

Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Xianze Fang , Jingnan Gao , Zhe Wang , Zhuo Chen , Xingyu Ren , Jiangjing Lyu , Qiaomu Ren , Zhonglei Yang , Xiaokang Yang , Yichao Yan , Chengfei Lyu

Underwater acoustic target recognition has emerged as a prominent research area within the field of underwater acoustics. However, the current availability of authentic underwater acoustic signal recordings remains limited, which hinders…

Sound · Computer Science 2024-11-06 Yuan Xie , Jiawei Ren , Junfeng Li , Ji Xu

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Darren Tsai , Julie Stephany Berrio , Mao Shan , Eduardo Nebot , Stewart Worrall

Photometric loss and pseudo-label-based self-training are two widely used methods for training stereo networks on unlabeled data. However, they both struggle to provide accurate supervision in occluded regions. The former lacks valid…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Peng Xu , Zhiyu Xiang , Tingming Bai , Tianyu Pu , Kai Wang , Chaojie Ji , Zhihao Yang , Eryun Liu

Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground truth annotations for depth completion settings can be difficult and, at the same time, a significant domain gap between real…

Computer Vision and Pattern Recognition · Computer Science 2020-08-06 Adrian Lopez-Rodriguez , Benjamin Busam , Krystian Mikolajczyk

While recent feed-forward 3D reconstruction models accelerate 3D reconstruction by jointly inferring dense geometry and camera poses in a single pass, their reliance on dense attention imposes a quadratic complexity, creating a prohibitive…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Weining Ren , Xiao Tan , Kai Han
‹ Prev 1 8 9 10 Next ›