English
Related papers

Related papers: Generalized Binary Search Network for Highly-Effic…

200 papers

High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Liupeng Li , Haoqian Kang , Zhenyu Lu , Jinpeng Wang , Bin Chen , Ke Chen , Yaowei Wang

Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-dimensional objects, and play an important role in many practical applications, such as image and video retrieval. We study the problem of learning…

Computer Vision and Pattern Recognition · Computer Science 2018-06-26 Fatih Cakir , Kun He , Sarah Adel Bargal , Stan Sclaroff

Feature selection is a crucial step in machine learning, especially for high-dimensional datasets, where irrelevant and redundant features can degrade model performance and increase computational costs. This paper proposes a novel…

Neural and Evolutionary Computing · Computer Science 2024-10-30 Azam Asilian Bidgoli , Shahryar Rahnamayan

Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search (BNAS), with a search space of…

Computer Vision and Pattern Recognition · Computer Science 2020-09-10 Hanlin Chen , Li'an Zhuo , Baochang Zhang , Xiawu Zheng , Jianzhuang Liu , Rongrong Ji , David Doermann , Guodong Guo

Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily…

Social and Information Networks · Computer Science 2023-01-02 Daokun Zhang , Jie Yin , Xingquan Zhu , Chengqi Zhang

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…

Computer Vision and Pattern Recognition · Computer Science 2018-07-17 Stepan Tulyakov , Anton Ivanov , Francois Fleuret

Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Rafael Brandt , Nicola Strisciuglio , Nicolai Petkov

Recent work in multi-view stereo (MVS) combines learnable photometric scores and regularization with PatchMatch-based optimization to achieve robust pixelwise estimates of depth, normals, and visibility. However, non-learning based methods…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Jae Yong Lee , Chuhang Zou , Derek Hoiem

Self-supervised monocular methods can efficiently learn depth information of weakly textured surfaces or reflective objects. However, the depth accuracy is limited due to the inherent ambiguity in monocular geometric modeling. In contrast,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-22 Xiaofeng Wang , Zheng Zhu , Guan Huang , Xu Chi , Yun Ye , Ziwei Chen , Xingang Wang

Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Abhishek Badki , Alejandro Troccoli , Kihwan Kim , Jan Kautz , Pradeep Sen , Orazio Gallo

PatchMatch Multi-View Stereo (PatchMatch MVS) is one of the popular MVS approaches, owing to its balanced accuracy and efficiency. In this paper, we propose Polarimetric PatchMatch multi-view Stereo (PolarPMS), which is the first method…

Computer Vision and Pattern Recognition · Computer Science 2023-11-15 Jinyu Zhao , Jumpei Oishi , Yusuke Monno , Masatoshi Okutomi

Learning accurate depth is essential to multi-view 3D object detection. Recent approaches mainly learn depth from monocular images, which confront inherent difficulties due to the ill-posed nature of monocular depth learning. Instead of…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Zengran Wang , Chen Min , Zheng Ge , Yinhao Li , Zeming Li , Hongyu Yang , Di Huang

Recent methods, such as 2D Gaussian Splatting and Gaussian Opacity Fields, have aimed to address the geometric inaccuracies of 3D Gaussian Splatting while retaining its superior rendering quality. However, these approaches still struggle to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jungeon Kim , Geonsoo Park , Seungyong Lee

In this paper, a complete pipeline for image-based 3D reconstruction of urban scenarios is proposed, based on PatchMatch Multi-View Stereo (MVS). Input images are firstly fed into an off-the-shelf visual SLAM system to extract camera poses…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Marco Orsingher , Paolo Zani , Paolo Medici , Massimo Bertozzi

We present MVLayoutNet, an end-to-end network for holistic 3D reconstruction from multi-view panoramas. Our core contribution is to seamlessly combine learned monocular layout estimation and multi-view stereo (MVS) for accurate layout…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Zhihua Hu , Bo Duan , Yanfeng Zhang , Mingwei Sun , Jingwei Huang

In this paper, we propose a novel binary-based cost computation and aggregation approach for stereo matching problem. The cost volume is constructed through bitwise operations on a series of binary strings. Then this approach is combined…

Computer Vision and Pattern Recognition · Computer Science 2014-02-11 Kang Zhang , Jiyang Li , Yijing Li , Weidong Hu , Lifeng Sun , Shiqiang Yang

We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes. Each cost volume is processed separately, and a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-05 Mahmoud Tahmasebi , Saif Huq , Kevin Meehan , Marion McAfee

We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), which measures the minimal amount of displacement an input…

Machine Learning · Computer Science 2019-11-19 Berry Weinstein , Shai Fine , Yacov Hel-Or

In biomedical science, a set of objects or persons can often be described by multiple distinct sets of features obtained from different data sources or modalities (called "multi-view data"). Classical machine learning methods ignore the…

Computation · Statistics 2025-04-25 Wouter van Loon

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Zhenlong Yuan , Jinguo Luo , Fei Shen , Zhaoxin Li , Cong Liu , Tianlu Mao , Zhaoqi Wang