13 Hits in 1.9 sec

gSLICr: SLIC superpixels at over 250Hz [article]

Carl Yuheng Ren and Victor Adrian Prisacariu and Ian D Reid
2015 arXiv   pre-print
We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Using a single graphic card, our implementation achieves speedups of up to 83× from the standard sequential implementation. Our implementation is fully compatible with the standard sequential implementation and the software is now available online and is open source.
arXiv:1509.04232v1 fatcat:abo2oxb6t5dijf75mzwx7iyomu

Robust Silhouette Extraction from Kinect Data [chapter]

Michele Pirovano, Carl Yuheng Ren, Iuri Frosio, Pier Luca Lanzi, Victor Prisacariu, David W. Murray, N. Alberto Borghese
2013 Lecture Notes in Computer Science  
Natural User Interfaces allow users to interact with virtual environments with little intermediation. Immersion becomes a vital need for such interfaces to be successful and it is achieved by making the interface invisible to the user. For cognitive rehabilitation, a mirror view is a good interface to the virtual world, but obtaining immersion is not straightforward. An accurate player profile, or silhouette, accurately extracted from the real-world background, increases both the visual quality
more » ... and the immersion of the player in the virtual environment. The Kinect SDK provides raw data that can be used to extract a simple player profile. In this paper, we present our method for obtaining a smooth player profile extraction from the Kinect image streams.
doi:10.1007/978-3-642-41181-6_65 fatcat:6gljk67suzhhjpfkp2erqxmys4

Regressing Local to Global Shape Properties for Online Segmentation and Tracking

Carl Yuheng Ren, Victor Prisacariu, Ian Reid
2013 International Journal of Computer Vision  
We propose a regression based learning framework that learns a set of shapes online, which can then be used to recover occluded object shapes. We represent shapes using their 2D discrete cosine transforms (DCT), and the key insight we propose is to regress low frequency harmonics, which represent the global properties of the shape, from high frequency harmonics, that encode the details of the object's shape. We learn the regression model using Locally Weighted Projection Regression (LWPR) which
more » ... expedites online, incremental learning. After sufficient observation of a set of unoccluded shapes, the learned model can detect occlusion and recover the full shapes from the occluded ones. Our shape regression method is linked to the pixel-wise posteriors (PWP) level set-based tracker of [1]. The PWP tracker obtains the target pose (a 6 DoF 2D affinity or 4 DoF 2D similarity transform) and figure/ground segmentation at each frame. We use the pose to align the shapes and then add them to the learning framework. After a burn-in period, the framework is able to recover occluded shapes at real time. We demonstrate the ideas using PWP tracker, however, the framework could be embedded in any segmentation-based tracking system. We use the DCT to represent a silhouette mask image (i.e. a binary image of the figure/ground segmentation, with 1 for foreground and -1 for background), so that the shape representation becomes a set of DCT coefficients. The transform yields a natural hierarchical representation of a shape in which the top-left, low frequency coefficients in the DCT capture the overall shape, while the high frequency coefficients (further away from top-left) capture the details of the shape. We use Locally Weighted Projection Regression (LWPR) [3] as our regression model. LWPR is based on the hypothesis that high dimensional data are characterized by locally low dimensional distribution. A learned LWPR has K local models, each comprising a Receptive Field (RF) characterized by a field center c k and a positive semi-definite distance metric D k that determines the size and shape of the neighborhood contributing to the local model; and a locally weighted partial least square (LWPLS) regression model characterized by a set of projections u k and respective their weights β k . Given a set of high frequency DCT coefficients as input x h f , the RF weight, also known as the activation, of the k th local model is computed as:
doi:10.1007/s11263-013-0635-y fatcat:xcw7nwrsbrhuxkbklbnlfc26wu

STAR3D: Simultaneous Tracking and Reconstruction of 3D Objects Using RGB-D Data

Carl Yuheng Ren, Victor Prisacariu, David Murray, Ian Reid
2013 2013 IEEE International Conference on Computer Vision  
We introduce a probabilistic framework for simultaneous tracking and reconstruction of 3D rigid objects using an RGB-D camera. The tracking problem is handled using a bag-of-pixels representation and a back-projection scheme. Surface and background appearance models are learned online, leading to robust tracking in the presence of heavy occlusion and outliers. In both our tracking and reconstruction modules, the 3D object is implicitly embedded using a 3D level-set function. The framework is
more » ... tialized with a simple shape primitive model (e.g. a sphere or a cube), and the real 3D object shape is tracked and reconstructed online. Unlike existing depth-based 3D reconstruction works, which either rely on calibrated/fixed camera set up or use the observed world map to track the depth camera, our framework can simultaneously track and reconstruct small moving objects. We use both qualitative and quantitative results to demonstrate the superior performance of both tracking and reconstruction of our method.
doi:10.1109/iccv.2013.197 dblp:conf/iccv/RenPMR13 fatcat:3dywhvyb4zg5tg2afkxzvjfgw4


Stuart Golodetz, Stephen L. Hicks, David W. Murray, Shahram Izadi, Philip H. S. Torr, Michael Sapienza, Julien P. C. Valentin, Vibhav Vineet, Ming-Ming Cheng, Victor A. Prisacariu, Olaf Kähler, Carl Yuheng Ren (+1 others)
2015 ACM SIGGRAPH 2015 Emerging Technologies on - SIGGRAPH '15  
Introduction We present a real-time, interactive system for the geometric reconstruction, object-class segmentation and learning of 3D scenes [Valentin et al. 2015 ]. Using our system, a user can walk into a room wearing a depth camera and a virtual reality headset, and both densely reconstruct the 3D scene [Newcombe et al. 2011; Nießner et al. 2013; Prisacariu et al. 2014] ) and interactively segment the environment into object classes such as 'chair', 'floor' and 'table'. The user interacts
more » ... ysically with the real-world scene, touching objects and using voice commands to assign them appropriate labels. These user-generated labels are leveraged by an online random forest-based machine learning algorithm, which is used to predict labels for previously unseen parts of the scene. The predicted labels, together with those provided directly by the user, are incorporated into a dense 3D conditional random field model, over which we perform mean-field inference to filter out label inconsistencies. The entire pipeline runs in real time, and the user stays 'in the loop' throughout the process, receiving immediate feedback about the progress of the labelling and interacting with the scene as necessary to refine the predicted segmentation. Background In this demo, we present an interactive approach to the exciting problem of real-time 3D scene segmentation, building on a large body of recent work in geometric scene reconstruction and scene understanding to showcase a system that can allow a user to segment an entire room in a very short period of time. Since we keep the user in the loop, our system can be used to produce high-quality segmentations of a real-world environment. Such segmentations have numerous uses, e.g. (i) we can use them to identify walkable surfaces in an environment as part of the process of generating a navigation map that can provide routing support to people or robots; (ii) we can use them to help partially-sighted people avoid collisions by highlighting the obstacles in an environment; (iii) in a computer vision setting, we can extract 3D models from them that can be used to train object detectors.
doi:10.1145/2782782.2792488 dblp:conf/siggraph/GolodetzSVVCPKR15 fatcat:dkxjyg54snbnjk2ckqg2evxbwa

Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices

Olaf Kahler, Victor Adrian Prisacariu, Carl Yuheng Ren, Xin Sun, Philip Torr, David Murray
2015 IEEE Transactions on Visualization and Computer Graphics  
E-mail: {olaf,victor,carl,dwm} remains challenging to provide the freedom of movement and instantaneous feedback of results that is crucial  ... 
doi:10.1109/tvcg.2015.2459891 pmid:26439825 fatcat:akbp63mmsfetbcb5kacwchwhsy

A Framework for the Volumetric Integration of Depth Images [article]

Victor Adrian Prisacariu, Olaf Kähler, Ming Ming Cheng, Carl Yuheng Ren, Julien Valentin, Philip H.S. Torr, Ian D. Reid, David W. Murray
2014 arXiv   pre-print
Volumetric models have become a popular representation for 3D scenes in recent years. One of the breakthroughs leading to their popularity was KinectFusion, where the focus is on 3D reconstruction using RGB-D sensors. However, monocular SLAM has since also been tackled with very similar approaches. Representing the reconstruction volumetrically as a truncated signed distance function leads to most of the simplicity and efficiency that can be achieved with GPU implementations of these systems.
more » ... wever, this representation is also memory-intensive and limits the applicability to small scale reconstructions. Several avenues have been explored for overcoming this limitation. With the aim of summarizing them and providing for a fast and flexible 3D reconstruction pipeline, we propose a new, unifying framework called InfiniTAM. The core idea is that individual steps like camera tracking, scene representation and integration of new data can easily be replaced and adapted to the needs of the user. Along with the framework we also provide a set of components for scalable reconstruction: two implementations of camera trackers, based on RGB data and on depth data, two representations of the 3D volumetric data, a dense volume and one based on hashes of subblocks, and an optional module for swapping subblocks in and out of the typically limited GPU memory.
arXiv:1410.0925v3 fatcat:gmz2swtjrjcbfn427ikjdgyur4

Author Index

2021 2021 IEEE International Conference on Robotics and Automation (ICRA)  
Ren, Yi .......... .......... .......... .......... .......... .......... 2761 Ren, Yuan .......... .......... .......... .......... .......... .......... ..........  ...  , Dongchun .......... .......... .......... .......... .......... .......... 3255 8287 Ren, Hao .......... .......... .......... .......... .......... .......... .......... 623 Ren, Hongliang .........  ... 
doi:10.1109/icra48506.2021.9561247 fatcat:ldcv75qzofes5ddwf6v2gyrmti

Acknowledgment to Reviewers of Agriculture in 2021

Agriculture Editorial Office
2022 Agriculture  
Despoina Beris Patcharin Songsri Despoina Petoumenou Patric Maurer Deyong Ren  ...  Suk Kim Carla Nati Min Xia Carla Rolo Antunes Mina Angelova Carles  ... 
doi:10.3390/agriculture12020188 fatcat:v5ry6pvkovazrabfcsowwwcpam

Novel CD44-targeting and pH/redox-dual-stimuli-responsive core–shell nanoparticles loading triptolide combats breast cancer growth and lung metastasis

Jinfeng Shi, Yali Ren, Jiaqi Ma, Xi Luo, Jiaxin Li, Yihan Wu, Huan Gu, Chaomei Fu, Zhixing Cao, Jinming Zhang
2021 Journal of Nanobiotechnology  
Hoechst 33,342 was provided by Suzhou Yuheng Biotechnology Co., Ltd. (Suzhou, China). HDD and BACy were purchased from Macklin Reagent Co., Ltd. (Shanghai, China).  ...  Finally, the membranes were mounted on microscope slides and images were captured using a fluorescence inverted microscope and a charge-coupled device camera (AxioCam HRC, Carl Zeiss, Oberkochen, Germany  ... 
doi:10.1186/s12951-021-00934-0 pmid:34162396 pmcid:PMC8220850 fatcat:bozr3tnf6rhdvevih4tuxmxwjm

SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments [article]

Hanjiang Hu, Baoquan Yang, Zhijian Qiao, Ding Zhao, Hesheng Wang
2021 arXiv   pre-print
Hu, Yuheng Qiu, Chen Wang, Yafei Hu, Ashish Kapoor, [33] Amir Atapour-Abarghouei and Toby P Breckon. Real- and Sebastian Scherer.  ...  Springer, 2016. [41] Weifeng Chen, Shengyi Qian, David Fan, Noriyuki [54] Yue Luo, Jimmy Ren, Mude Lin, Jiahao Pang, Wenxiu Kojima, Max Hamilton, and Jia Deng.  ... 
arXiv:2011.04408v5 fatcat:vout2lb2lffrdlpgte2zk3omoi

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning [article]

Ajinkya Tejankar, Soroush Abbasi Koohpayegani, KL Navaneet, Kossar Pourahmadi, Akshayvarun Subramanya, Hamed Pirsiavash
2021 arXiv   pre-print
Razavi, Carl Doersch, SM Eslami, and Aaron van den Oord. Blaschko, and Andrea Vedaldi.  ...  In [39] Yuheng Jia, Junhui Hou, and Sam Kwong. Constrained European Conference on Computer Vision, pages 69–84.  ... 
arXiv:2112.04607v1 fatcat:n7g5f2obnzf6xjn6jpyjpp4ezu

Structured Directional Pruning via Perturbation Orthogonal Projection [article]

Yinchuan Li, Xiaofeng Liu, Yunfeng Shao, Qing Wang, Yanhui Geng
2021 arXiv   pre-print
[2] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition.  ...  [9] Carl Lemaire, Andrew Achkar, and Pierre-Marc Jodoin. Structured pruning of neural networks with budget-aware regularization.  ... 
arXiv:2107.05328v2 fatcat:dmk2hvczinh3llvraam5aobq4y