|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | PCT:Point cloud transformer显示文摘The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing.This paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud learning.PCT is based on Transformer,which achieves huge success in natural language processing and displays great potential in image processing.It is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud learning.To better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor search.Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks. | Meng-Hao Guo Jun-Xiong Cai Zheng-Ning Liu Tai-Jiang Mu Ralph R.Martin Shi-Min Hu | 2021 | Computational Visual Media2021，7，2： | 55 |
| 2 | Attention mechanisms in computer vision:A survey显示文摘Humans can naturally and effectively find salient regions in complex scenes.Motivated by this observation,attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system.Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image.Attention mechanisms have achieved great success in many visual tasks,including image classification,object detection,semantic segmentation,video understanding,image generation,3D vision,multimodal tasks,and self-supervised learning.In this survey,we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach,such as channel attention,spatial attention,temporal attention,and branch attention;a related repository http://gffzz188fe103f8f1460asokf66bnbkq6p6690.ffgz.tsg.suse.edu.cn/MenghaoG uo/Awesome-Vision-Attentions is dedicated to collecting related work.We also suggest future directions for attention mechanism research. | Meng-Hao Guo Tian-Xing Xu Jiang-Jiang Liu Zheng-Ning Liu Peng-Tao Jiang Tai-Jiang Mu Song-Hai Zhang Ralph R.Martin Ming-Ming Cheng Shi-Min Hu | 2022 | Computational Visual Media2022，8，3： | 27 |
| 3 | 3D modeling and motion parallax for improved videoconferencing显示文摘We consider a face-to-face videoconferencing system that uses a Kinect camera at each end of the link for 3D modeling and an ordinary2 D display for output. The Kinect camera allows a 3D model of each participant to be transmitted;the(assumed static) background is sent separately.Furthermore, the Kinect tracks the receiver's head,allowing our system to render a view of the sender depending on the receiver's viewpoint. The resulting motion parallax gives the receivers a strong impression of 3D viewing as they move, yet the system only needs an ordinary 2D display. This is cheaper than a full3 D system, and avoids disadvantages such as the need to wear shutter glasses, VR headsets, or to sit in a particular position required by an autostereo display.Perceptual studies show that users experience a greater sensation of depth with our system compared to a typical 2D videoconferencing system. | Zhe Zhu Ralph R.Martin Robert Pepperell Alistair Burleigh | 2016 | Computational Visual Media2016，2，2： | 7 |
| 4 | Panorama completion for street views显示文摘This paper considers panorama images used for street views. Their viewing angle of 360° causes pixels at the top and bottom to appear stretched and warped. Although current image completion algorithms work well, they cannot be directly used in the presence of such distortions found in panoramas of street views. We thus propose a novel approach to complete such 360° panoramas using optimizationbased projection to deal with distortions. Experimental results show that our approach is efficient and provides an improvement over standard image completion algorithms. | Zhe Zhu Ralph R.Martin Shi-Min Hu | 2015 | Computational Visual Media2015，1，1： | 6 |
| 5 | Evaluation for Small Visual Difference Between Conforming Meshes on Strain Field显示文摘This paper gives a method of quantifying small visual differences between 3D mesh models with conforming topology, based on the theory of strain fields. Strain field is a geometric quantity in elasticity which is used to describe the deformation of elastomer. In this paper we consider the 3D models as objects with elasticity. The further demonstrations are provided: the first is intended to give the reader a visual impression of how our measure works in practice; and the second is to give readers a visual impression of how our measure works in evaluating filter algorithms. Our experiments show that our difference estimates are well correlated with human perception of differences. This work has applications in the evaluation of 3D mesh watermarking, 3D mesh compression reconstruction, and 3D mesh filtering. | 边哲 胡事民 Ralph R.Martin | 2009 | Journal of Computer Science & Technology2009，24，1： | 4 |
| 6 | Skeleton-based canonical forms for non-rigid 3D shape retrieval显示文摘The retrieval of non-rigid 3D shapes is an important task. A common technique is to simplify this problem to a rigid shape retrieval task by producing a bending-invariant canonical form for each shape in the dataset to be searched. It is common for these techniques to attempt to 'unbend' a shape by applying multidimensional scaling(MDS) to the distances between points on the mesh, but this leads to unwanted local shape distortions. We instead perform the unbending on the skeleton of the mesh, and use this to drive the deformation of the mesh itself. This leads to computational speed-up, and reduced distortion of local shape detail. We compare our method against other canonical forms: our experiments show that our method achieves state-of-the-art retrieval accuracy in a recent canonical forms benchmark, and only a small drop in retrieval accuracy over the state-of-the-art in a second recent benchmark, while being significantly faster. | David Pickup Xianfang Sun Paul L.Rosin Ralph R.Martin | 2016 | Computational Visual Media2016，2，3： | 1 |
| 7 | Livestock detection in aerial images using a fully convolutional network显示文摘In order to accurately count the number of animals grazing on grassland, we present a livestock detection algorithm using modified versions of U-net and Google Inception-v4 net. This method works well to detect dense and touching instances. We also introduce a dataset for livestock detection in aerial images, consisting of 89 aerial images collected by quadcopter. Each image has resolution of about 3000 ×4000 pixels, and contains livestock with varying shapes,scales, and orientations.We evaluate our method by comparison against Faster RCNN and Yolo-v3 algorithms using our aerial livestock dataset. The average precision of our method is better than Yolo-v3 and is comparable to Faster RCNN. | Liang Han Pin Tao Ralph R.Martin | 2019 | Computational Visual Media2019，5，2： | 1 |
| 8 | Comfort-driven disparity adjustment for stereoscopic video显示文摘Pixel disparity—the offset of corresponding pixels between left and right views—is a crucial parameter in stereoscopic three-dimensional(S3D)video, as it determines the depth perceived by the human visual system(HVS). Unsuitable pixel disparity distribution throughout an S3 D video may lead to visual discomfort. We present a unified and extensible stereoscopic video disparity adjustment framework which improves the viewing experience for an S3 D video by keeping the perceived 3D appearance as unchanged as possible while minimizing discomfort. We first analyse disparity and motion attributes of S3 D video in general, then derive a wide-ranging visual discomfort metric from existing perceptual comfort models. An objective function based on this metric is used as the basis of a hierarchical optimisation method to find a disparity mapping function for each input video frame. Warping-based disparity manipulation is then applied to the input video to generate the output video, using the desired disparity mappings as constraints. Our comfort metric takes into account disparity range, motion, and stereoscopic window violation; the framework could easily be extended to use further visual comfort models. We demonstrate the power of our approach using both animated cartoons and real S3 D videos. | Miao Wang Xi-Jin Zhang Jun-Bang Liang Song-Hai Zhang Ralph R.Martin | 2016 | Computational Visual Media2016，2，1： | 1 |
| 9 | Can attention enable MLPs to catch up with CNNs?显示文摘In the first week of May 2021,researchers from four different institutions:Google,Tsinghua University,Oxford University,and Facebook shared their latest work[1–4]on ar Xiv.org at almost the same time,each proposing new learning architectures,consisting mainly of linear layers,claiming them to be comparable or superior to convolutional-based models. | Meng-Hao Guo Zheng-Ning Liu Tai-Jiang Mu Dun Liang Ralph R.Martin Shi-Min Hu | 2021 | Computational Visual Media2021，7，3： | 1 |
| 10 | As-Rigid-As-Possible Surface Morphing显示文摘This paper presents a new morphing method based on the 'as-rigid-as-possible' approach.Unlike the original as-rigid-as-possible method,we avoid the need to construct a consistent tetrahedral mesh,but instead require a consistent triangle surface mesh and from it create a tetrahedron for each surface triangle.Our new approach has several significant advantages.It is much easier to create a consistent triangle mesh than to create a consistent tetrahedral mesh.Secondly,the equations arising from our approach can be solved much more efficiently than the corresponding equations for a tetrahedral mesh.Finally,by incorporating the translation vector in the energy functional controlling interpolation,our new method does not need the user to arbitrarily fix any vertex to obtain a solution,allowing artists automatic control of interpolated mesh positions. | 刘亚姝 严寒冰 Ralph R.Martin | 2011 | Journal of Computer Science & Technology2011，26，3： | 0 |
| 11 | Robust tracking-by-detection using a selection and completion mechanism显示文摘It is challenging to track a target continuously in videos with long-term occlusion,or objects which leave then re-enter a scene.Existing tracking algorithms combined with onlinetrained object detectors perform unreliably in complex conditions, and can only provide discontinuous trajectories with jumps in position when the object is occluded. This paper proposes a novel framework of tracking-by-detection using selection and completion to solve the abovementioned problems. It has two components, tracking and trajectory completion. An offline-trained object detector can localize objects in the same category as the object being tracked. The object detector is based on a highly accurate deep learning model. The object selector determines which object should be used to re-initialize a traditional tracker. As the object selector is trained online,it allows the framework to be adaptable. During completion, a predictive non-linear autoregressive neural network completes any discontinuous trajectory.The tracking component is an online real-time algorithm, and the completion part is an after-theevent mechanism. Quantitative experiments show a significant improvement in robustness over prior stateof-the-art methods. | Ruochen Fan Fang-Lue Zhang Min Zhang Ralph R.Martin | 2017 | Computational Visual Media2017，3，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员