中文
相关论文

相关论文: Spherical Vision Transformer for 360-degree Video …

200 篇论文

Omnidirectional 360{\deg} camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV). However, corresponding 360{\deg} depth sensors, which are also critical…

计算机视觉与模式识别 · 计算机科学 2020-07-06 Xinjing Cheng , Peng Wang , Yanqi Zhou , Chenye Guan , Ruigang Yang

Omnidirectional images (also referred to as static 360{\deg} panoramas) impose viewing conditions much different from those of regular 2D images. How do humans perceive image distortions in immersive virtual reality (VR) environments is an…

图像与视频处理 · 电气工程与系统科学 2021-01-06 Xiangjie Sui , Kede Ma , Yiru Yao , Yuming Fang

We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes. Existing approaches to object-centric representation learning show limitations in generalizing to larger scenes as their learning processes…

计算机视觉与模式识别 · 计算机科学 2023-09-26 Tianyu Wang , Kee Siong Ng , Miaomiao Liu

Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and…

计算机视觉与模式识别 · 计算机科学 2017-08-07 Trung-Nghia Le , Akihiro Sugimoto

Omnidirectional images (ODIs) are commonly used in real-world visual tasks, and high-resolution ODIs help improve the performance of related visual tasks. Most existing super-resolution methods for ODIs use end-to-end learning strategies,…

计算机视觉与模式识别 · 计算机科学 2024-04-18 Runyi Li , Xuhan Sheng , Weiqi Li , Jian Zhang

Single-view depth estimation from omnidirectional images has gained popularity with its wide range of applications such as autonomous driving and scene reconstruction. Although data-driven learning-based methods demonstrate significant…

计算机视觉与模式识别 · 计算机科学 2022-02-17 Qi Feng , Hubert P. H. Shum , Shigeo Morishima

360-degree streaming videos can provide a rich immersive experiences to the users. However, it requires an extremely high bandwidth network. One of the common solutions for saving bandwidth consumption is to stream only a portion of video…

多媒体 · 计算机科学 2022-06-07 Chuanzhe Jing , Tho Nguyen Duc , Phan Xuan Tan , Eiji Kamioka

In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in stark contrast to the human eye's efficient information…

计算机视觉与模式识别 · 计算机科学 2025-09-11 Yuguang Zhang , Qihang Fan , Huaibo Huang

A new approach to seismic interpretation is proposed to leverage visual perception and human visual system modeling. Specifically, a saliency detection algorithm based on a novel attention model is proposed for identifying subsurface…

计算机视觉与模式识别 · 计算机科学 2022-01-19 Muhammad Amir Shafiq , Zhiling Long , Haibin Di , Ghassan AlRegib

Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on…

计算机视觉与模式识别 · 计算机科学 2021-05-25 Lu He , Qianyu Zhou , Xiangtai Li , Li Niu , Guangliang Cheng , Xiao Li , Wenxuan Liu , Yunhai Tong , Lizhuang Ma , Liqing Zhang

Video object segmentation aims at accurately segmenting the target object regions across consecutive frames. It is technically challenging for coping with complicated factors (e.g., shape deformations, occlusion and out of the lens). Recent…

计算机视觉与模式识别 · 计算机科学 2019-07-03 Peng Sun , Peiwen Lin , Guangliang Cheng , Jianping Shi , Jiawan Zhang , Xi Li

The Vision Transformer (ViT) architecture has become widely recognized in computer vision, leveraging its self-attention mechanism to achieve remarkable success across various tasks. Despite its strengths, ViT's optimization remains…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Haoyu Yun , Hamid Krim

Omnidirectional image (ODI) data is captured with a 360x180 field-of-view, which is much wider than the pinhole cameras and contains richer spatial information than the conventional planar images. Accordingly, omnidirectional vision has…

计算机视觉与模式识别 · 计算机科学 2022-05-25 Hao Ai , Zidong Cao , Jinjing Zhu , Haotian Bai , Yucheng Chen , Lin Wang

We propose a new method for the visual quality assessment of 360-degree (omnidirectional) videos. The proposed method is based on computing multiple spatio-temporal objective quality features on viewports extracted from 360-degree videos. A…

多媒体 · 计算机科学 2021-05-04 Roberto G. de A. Azevedo , Neil Birkbeck , Ivan Janatra , Balu Adsumilli , Pascal Frossard

Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Junsong Zhang , Zisong Chen , Chunyu Lin , Lang Nie , Zhijie Shen , Kang Liao , Junda Huang , Yao Zhao

Omnidirectional 3D Gaussian Splatting with panoramas is a key technique for 3D scene representation, and existing methods typically rely on slow SfM to provide camera poses and sparse points priors. In this work, we propose a pose-free…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Chuanqing Zhuang , Xin Lu , Zehui Deng , Zhengda Lu , Yiqun Wang , Junqi Diao , Jun Xiao

Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models remains challenging, as existing formulations are designed for…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Zhe Yang , Guoqiang Zhao , Sheng Wu , Kai Luo , Kailun Yang

Understanding and predicting the human visual attentional mechanism is an active area of research in the fields of neuroscience and computer vision. In this work, we propose DeepFix, a first-of-its-kind fully convolutional neural network…

计算机视觉与模式识别 · 计算机科学 2015-10-13 Srinivas S. S. Kruthiventi , Kumar Ayush , R. Venkatesh Babu

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with…

计算机视觉与模式识别 · 计算机科学 2023-04-26 Angelika Ando , Spyros Gidaris , Andrei Bursuc , Gilles Puy , Alexandre Boulch , Renaud Marlet

Omni-directional cameras have many advantages overconventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have beenproposed recently to apply convolutional neural networks(CNNs) to…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Yeonkun Lee , Jaeseok Jeong , Jongseob Yun , Wonjune Cho , Kuk-Jin Yoon