English
Related papers

Related papers: Cross-view Domain Generalization via Geometric Con…

200 papers

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Xidong Peng , Runnan Chen , Feng Qiao , Lingdong Kong , Youquan Liu , Yujing Sun , Tai Wang , Xinge Zhu , Yuexin Ma

Semantic segmentation of aerial point cloud data can be utilised to differentiate which points belong to classes such as ground, buildings, or vegetation. Point clouds generated from aerial sensors mounted to drones or planes can utilise…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Matthew Howe , Boris Repasky , Timothy Payne

Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation have shown promise,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Mengzhu Wang , Changyuan Deng , Shanshan Wang , Nan Yin , Long Lan , Liang Yang

This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint…

Computer Vision and Pattern Recognition · Computer Science 2017-05-17 Jing Zhang , Wanqing Li , Philip Ogunbona

Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time, photorealistic scene reconstruction. However, conventional 3DGS frameworks typically rely on sparse point clouds derived from Structure-from-Motion (SfM), which…

Graphics · Computer Science 2026-03-25 Yan Fang , Jianfei Ge , Jiangjian Xiao

Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Sungjune Park , Yeongyun Kim , Se Yeon Kim , Yong Man Ro

Instance-level object segmentation across disparate egocentric and exocentric views is a fundamental challenge in visual understanding, critical for applications in embodied AI and remote collaboration. This task is exceptionally difficult…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Yulu Gao , Bohao Zhang , Zongheng Tang , Jitong Liao , Wenjun Wu , Si Liu

Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Christoph Hümmer , Manuel Schwonberg , Liangwei Zhou , Hu Cao , Alois Knoll , Hanno Gottschalk

Single-domain generalization for object detection (S-DGOD) seeks to transfer learned representations from a single source domain to unseen target domains. While recent approaches have primarily focused on achieving feature invariance, they…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Zhenwei He , Hongsu Ni

Autonomous vehicles need to have a semantic understanding of the three-dimensional world around them in order to reason about their environment. State of the art methods use deep neural networks to predict semantic classes for each point in…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Larissa T. Triess , David Peter , Christoph B. Rist , J. Marius Zöllner

Generalized zero-shot learning (GZSL) focuses on recognizing seen and unseen classes against domain shift problem where data of unseen classes may be misclassified as seen classes. However, existing GZSL is still limited to seen domains. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Jiaqi Yue , Chunhui Zhao , Jiancheng Zhao , Biao Huang

Cross-view geo-localization (CVGL) is pivotal for GNSS-denied UAV navigation but remains brittle under the drastic geometric misalignment between oblique aerial views and orthographic satellite references. Existing methods predominantly…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Minglei Li , Mengfan He , Chunyu Li , Chao Chen , Xingyu Shao , Ziyang Meng

Learning meaningful local and global information remains a challenge in point cloud segmentation tasks. When utilizing local information, prior studies indiscriminately aggregates neighbor information from different classes to update query…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Abiao Li , Chenlei Lv , Guofeng Mei , Yifan Zuo , Jian Zhang , Yuming Fang

Novel View Synthesis (NVS) can reconstruct scenes from multi-view images and synthesize novel images from new viewpoints, which provides technical support for tasks such as target recognition and environmental perception. Aerial remote…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Yiling Yao , Bing Zhang , Wenjuan Zhang , Lianru Gao , Dailiang Peng , Bocheng Li , Yaning Wang , Bowen Wang

Recent works on 3D semantic segmentation propose to exploit the synergy between images and point clouds by processing each modality with a dedicated network and projecting learned 2D features onto 3D points. Merging large-scale point clouds…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Damien Robert , Bruno Vallet , Loic Landrieu

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the \textit{de facto} method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Chenfeng Xu , Bichen Wu , Zining Wang , Wei Zhan , Peter Vajda , Kurt Keutzer , Masayoshi Tomizuka

Semi-supervised semantic segmentation (SSSS) is vital in computational pathology, where dense annotations are costly and limited. Existing methods often rely on pixel-level consistency, which propagates noisy pseudo-labels and produces…

Image and Video Processing · Electrical Eng. & Systems 2025-11-14 Ha-Hieu Pham , Minh Le , Han Huynh , Nguyen Quoc Khanh Le , Huy-Hieu Pham

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Shaocong Long , Qianyu Zhou , Xiangtai Li , Chenhao Ying , Yunhai Tong , Lizhuang Ma , Yuan Luo , Dacheng Tao

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Xiaohan Zhang , Xingyu Li , Waqas Sultani , Yi Zhou , Safwan Wshah

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Seogkyu Jeon , Kibeom Hong , Hyeran Byun
‹ Prev 1 4 5 6 7 8 10 Next ›