中文
相关论文

相关论文: SGFormer: Satellite-Ground Fusion for 3D Semantic …

200 篇论文

Vision-based 3D semantic scene completion (SSC) describes autonomous driving scenes through 3D volume representations. However, the occlusion of invisible voxels by scene surfaces poses challenges to current SSC methods in hallucinating…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Xiao Zhao , Bo Chen , Mingyang Sun , Dingkang Yang , Youxing Wang , Xukun Zhang , Mingcheng Li , Dongliang Kou , Xiaoyi Wei , Lihua Zhang

Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Yi Chen , Tianchen Deng , Wentao Zhao , Xiaoning Wang , Wenqian Xi , Weidong Chen , Jingchuan Wang

4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Xiaokai Bai , Lianqing Zheng , Si-Yuan Cao , Xiaohan Zhang , Zhe Wu , Beinan Yu , Fang Wang , Jie Bai , Hui-Liang Shen

We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce…

机器人学 · 计算机科学 2024-03-29 Siting Zhu , Guangming Wang , Hermann Blum , Jiuming Liu , Liang Song , Marc Pollefeys , Hesheng Wang

Inferring the 3D geometry and the semantic meaning of surfaces, which are occluded, is a very challenging task. Recently, a first end-to-end learning approach has been proposed that completes a scene from a single depth image. The approach…

计算机视觉与模式识别 · 计算机科学 2019-05-16 Martin Garbade , Yueh-Tung Chen , Johann Sawatzky , Juergen Gall

This paper presents a system for autonomous semantic exploration and dense semantic target mapping of a complex unknown environment using a ground robot equipped with a LiDAR-panoramic camera suite. Existing approaches often struggle to…

机器人学 · 计算机科学 2025-09-19 Xiaoyang Zhan , Shixin Zhou , Qianqian Yang , Yixuan Zhao , Hao Liu , Srinivas Chowdary Ramineni , Kenji Shimada

Recent studies have shown the benefits of using additional elevation data (e.g., DSM) for enhancing the performance of the semantic segmentation of aerial images. However, previous methods mostly adopt 3D elevation information as additional…

计算机视觉与模式识别 · 计算机科学 2020-09-23 Xiang Li , Lingjing Wang , Yi Fang

Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination. However, they still struggle with non-uniform lighting scenarios, such as backlit and shadow, appearing as over-exposure…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Hanting Li , Fei Zhou , Xin Sun , Yang Hua , Jungong Han , Liang-Jie Zhang

Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Jie Luo , Yuxuan Jiang , Xin Jin , Mingyu Liu , Yihui Fan

Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic…

计算机视觉与模式识别 · 计算机科学 2020-02-25 Xiangtai Li , Houlong Zhao , Lei Han , Yunhai Tong , Kuiyuan Yang

Unmanned Aerial Vehicles (UAVs) hold immense potential for critical applications, such as search and rescue operations, where accurate perception of indoor environments is paramount. However, the concurrent amalgamation of localization, 3D…

机器人学 · 计算机科学 2024-01-17 Thanh Nguyen Canh , Van-Truong Nguyen , Xiem HoangVan , Armagan Elibol , Nak Young Chong

We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow,…

计算机视觉与模式识别 · 计算机科学 2020-10-27 Luis Roldão , Raoul de Charette , Anne Verroust-Blondet

Establishing accurate point-to-point correspondences between non-rigid 3D shapes remains a critical challenge, particularly under non-isometric deformations and topological noise. Existing functional map pipelines suffer from ambiguities…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Tianwei Ye , Xiaoguang Mei , Yifan Xia , Fan Fan , Jun Huang , Jiayi Ma

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in AI systems, we propose VoxFormer, a Transformer-based…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Yiming Li , Zhiding Yu , Christopher Choy , Chaowei Xiao , Jose M. Alvarez , Sanja Fidler , Chen Feng , Anima Anandkumar

High-resolution remote sensing images contain densely distributed objects with pronounced scale variations and complex boundaries, which impose higher demands on both the geometric localization and semantic prediction capabilities of…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Jianzheng Wang , Huan Ni

The following is a technical report to test the validity of the proposed Subspace Pyramid Fusion Module (SPFM) to capture multi-scale feature representations, which is more useful for semantic segmentation. In this investigation, we have…

计算机视觉与模式识别 · 计算机科学 2023-12-07 Mohammed A. M. Elhassan , Chenhui Yang , Chenxi Huang , Tewodros Legesse Munea

Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fully leverage global and local semantic information for…

计算机视觉与模式识别 · 计算机科学 2023-07-18 Lei Pan , Wuyang Luan , Yuan Zheng , Qiang Fu , Junhui Li

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to…

计算机视觉与模式识别 · 计算机科学 2018-03-29 Angela Dai , Daniel Ritchie , Martin Bokeloh , Scott Reed , Jürgen Sturm , Matthias Nießner

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle's surroundings.…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Helin Cao , Sven Behnke

The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fundamental limitation: they cannot produce 3D worlds that…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Antoine Schnepf , Karim Kassab , Flavian Vasile , Andrew Comport