English
Related papers

Related papers: ASAP: Accurate semantic segmentation for real time…

200 papers

We study multi-sensor fusion for 3D semantic segmentation that is important to scene understanding for many applications, such as autonomous driving and robotics. Existing fusion-based methods, however, may not achieve promising performance…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Mingkui Tan , Zhuangwei Zhuang , Sitao Chen , Rong Li , Kui Jia , Qicheng Wang , Yuanqing Li

Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains non-trivial to thoroughly utilize the multi-level…

Computer Vision and Pattern Recognition · Computer Science 2018-12-05 Yunzhi Zhuge , Pingping Zhang , Huchuan Lu

Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations. Current multi-sensor deep learning based semantic segmentation approaches do not provide…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Hermann Blum , Abel Gawel , Roland Siegwart , Cesar Cadena

Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{concise} and…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Hui-Xian Cheng , Xian-Feng Han , Guo-Qiang Xiao

Conventional point cloud semantic segmentation methods usually employ an encoder-decoder architecture, where mid-level features are locally aggregated to extract geometric information. However, the over-reliance on these class-agnostic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-27 Ziyi Wang , Yongming Rao , Xumin Yu , Jie Zhou , Jiwen Lu

Forecasting the future behavior of all traffic agents in the vicinity is a key task to achieve safe and reliable autonomous driving systems. It is a challenging problem as agents adjust their behavior depending on their intentions, the…

Robotics · Computer Science 2021-12-30 Edoardo Mello Rella , Jan-Nico Zaech , Alexander Liniger , Luc Van Gool

This paper presents a real-time online vision framework to jointly recover an indoor scene's 3D structure and semantic label. Given noisy depth maps, a camera trajectory, and 2D semantic labels at train time, the proposed deep neural…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Davide Menini , Suryansh Kumar , Martin R. Oswald , Erik Sandstrom , Cristian Sminchisescu , Luc Van Gool

Features from multiple scales can greatly benefit the semantic edge detection task if they are well fused. However, the prevalent semantic edge detection methods apply a fixed weight fusion strategy where images with different semantics are…

Computer Vision and Pattern Recognition · Computer Science 2019-02-26 Yuan Hu , Yunpeng Chen , Xiang Li , Jiashi Feng

Semantic segmentation works on the computer vision algorithm for assigning each pixel of an image into a class. The task of semantic segmentation should be performed with both accuracy and efficiency. Most of the existing deep FCNs yield to…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Farshad Safavi , Irfan Ali , Venkatesh Dasari , Guanqun Song , Ting Zhu , Maryam Rahnemoonfar

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…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Mohammed A. M. Elhassan , Chenhui Yang , Chenxi Huang , Tewodros Legesse Munea

Semantic segmentation in complex environments such as urban driving scenes remains challenging under adverse lighting conditions, where RGB images alone provide insufficient information. RGB-Thermal fusion leverages the complementary…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 İsmail Emre Canıtez , Özgür Erkent

Indoor scenes are usually characterized by scattered objects and their relationships, which turns the indoor scene classification task into a challenging computer vision task. Despite the significant performance boost in classification…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Ricardo Pereira , Luís Garrote , Tiago Barros , Ana Lopes , Urbano J. Nunes

As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance. Recently, due to the increasing demand for autonomous systems and robots, it is significant to make…

Computer Vision and Pattern Recognition · Computer Science 2019-10-02 Gen Li , Inyoung Yun , Jonghyun Kim , Joongkyu Kim

In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Sravan Kumar Jagadeesh , René Schuster , Didier Stricker

Thanks to the advantages of the friendly annotations and the satisfactory performance, Weakly-Supervised Semantic Segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS was awakened to alleviate…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Chunyan Wang , Dong Zhang , Liyan Zhang , Jinhui Tang

State-of-the-art crowd counting models follow an encoder-decoder approach. Images are first processed by the encoder to extract features. Then, to account for perspective distortion, the highest-level feature map is fed to extra components…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Yiming Ma , Victor Sanchez , Tanaya Guha

LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Chaoqun Wang , Xiaobin Hong , Wenzhong Li , Ruimao Zhang

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Qingfeng Liu , Mostafa El-Khamy , Dongwoon Bai , Jungwon Lee

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Yaoyan Zheng , Hongyu Yang , Di Huang

Expanding the receptive field in a deep learning model for large-scale 3D point cloud segmentation is an effective technique for capturing rich contextual information, which consequently enhances the network's ability to learn meaningful…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Haodong Wang , Chongyu Wang , Yinghui Quan , Di Wang