56 Hits in 6.7 sec

Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data [article]

Li Sun and Cheng Zhao and Rustam Stolkin
2017 arXiv   pre-print
) with non-parametric models (Gaussian Process Classification).  ...  To overcome this problem, we propose a novel, weakly-supervised learning architecture (DCNN-GPC) which combines parametric models (a pair of Deep Convolutional Neural Networks (DCNN) for RGB and D modalities  ...  Zhao was sponsored by DISTINCTIVE -a university consortium funded by the Research Councils UK Energy programme. Stolkin was sponsored by a Royal Society Industry Fellowship.  ... 
arXiv:1703.06370v1 fatcat:of7fqod2u5belo2mqblewq3th4

Leaving Flatland: Advances in 3D behavioral measurement [article]

Jesse D. Marshall, Tianqing Li, Joshua H. Wu, Timothy W. Dunn
2021 arXiv   pre-print
Continued advances at the intersection of deep learning and computer vision will facilitate 3D tracking across more anatomical features, with less training data, in additional species, and within more  ...  Existing 3D measurement techniques draw on specialized hardware, such as motion capture or depth cameras, as well as deep multi-view and monocular computer vision.  ...  RGBD-Dog acquires ground-truth shape in behaving canines via motion capture and depth imaging [23] , which they use to train and validate a CNN predicting shape from one color and one depth image.  ... 
arXiv:2112.01987v1 fatcat:z5dqj47s3fbt3d4t75bnsp2l6q

Multiview Cross-supervision for Semantic Segmentation [article]

Yuan Yao, Hyun Soo Park
2018 arXiv   pre-print
This paper presents a semi-supervised learning framework for a customized semantic segmentation task using multiview image streams.  ...  We validate this network by recognizing a customized semantic category per pixel from realworld visual data including non-human species and a subject of interest in social videos where attaining large-scale  ...  Result We validate our semi-supervised semantic segmentation framework using real-world data on human and non-human species including a subject of interest in social videos with three different multi-camera  ... 
arXiv:1812.01738v1 fatcat:f444ktnemfcxrnihuint4vvw7e

HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video [article]

Chung-Yi Weng, Brian Curless, Pratul P. Srinivasan, Jonathan T. Barron, Ira Kemelmacher-Shlizerman
2022 arXiv   pre-print
Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via  ...  We show significant performance improvements over prior work, and compelling examples of free-viewpoint renderings from monocular video of moving humans in challenging uncontrolled capture scenarios.  ...  [44] reduced the number of required input frames to as few as a single RGBD image via semi-parametric learning. Wu et al. [67] and Peng et al.  ... 
arXiv:2201.04127v1 fatcat:6r3usqxar5delnfsusil4lm344

NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing [article]

Jiakai Zhang, Liao Wang, Xinhang Liu, Fuqiang Zhao, Minzhang Li, Haizhao Dai, Boyuan Zhang, Wei Yang, Lan Xu, Jingyi Yu
2022 arXiv   pre-print
In this paper, we present a neural volumography technique called neural volumetric video or NeuVV to support immersive, interactive, and spatial-temporal rendering of volumetric video contents with photo-realism  ...  Real-time NeuVV rendering further enables a class of immersive content editing tools.  ...  [Peng et al. 2021; use the parametric human model as prior to learn a dynamic radiance field for human body using sparse views as inputs.  ... 
arXiv:2202.06088v1 fatcat:23qn5ffx6raglmp363hz5iizne

Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos [article]

Yasamin Jafarian, Hyun Soo Park
2021 arXiv   pre-print
A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results  ...  Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry.  ...  Acknowledgement This work was supported by a NSF NRI 2022894 and NSF CAREER 1846031.  ... 
arXiv:2103.03319v2 fatcat:rl2jacd3gvgqfbteglmozl5ub4

Guest Editors' Introduction to the Special Issue on RGB-D Vision: Methods and Applications

Mohammed Bennamoun, Yulan Guo, Federico Tombari, Kamal Youcef-Toumi, Ko Nishino
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Ç R GB-D vision is an emerging research topic in computer vision, with a number of applications in robotics, entertainment, biometrics and multimedia.  ...  Bennamoun is with the  ...  and the optimized human body shape from a single depth camera.  ... 
doi:10.1109/tpami.2020.2976227 fatcat:dqt5dt3ymnesfikmgu2sxffdcu

State of the Art on Neural Rendering [article]

Ayush Tewari, Ohad Fried, Justus Thies, Vincent Sitzmann, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nießner, Rohit Pandey, Sean Fanello (+7 others)
2020 arXiv   pre-print
Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering  ...  Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches.  ...  However this capture technology is still far from being accessible to a typical consumer who, at best, may own a single RGBD sensor such as a Kinect.  ... 
arXiv:2004.03805v1 fatcat:6qs7ddftkfbotdlfd4ks7llovq

Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph [article]

Xin Yu, Jeroen van Baar, Siheng Chen
2021 arXiv   pre-print
We recognize that the connection between coarse and dense is itself a graph, and introduce graph fusion blocks to exchange information between graphs with different scales.  ...  We train our model end-to-end and show that we can achieve state-of-the-art results for several evaluation datasets.  ...  In of humans with a single rgbd camera via semi-parametric IEEE Conf. Comput. Vis. Pattern Recog., June 2019. 2 learning. In IEEE Conf. Comput. Vis.  ... 
arXiv:2110.08472v2 fatcat:mnhfcnawsrdyhktfpdltavi7sq

Detailed Avatar Recovery from Single Image [article]

Hao Zhu and Xinxin Zuo and Haotian Yang and Sen Wang and Xun Cao and Ruigang Yang
2021 arXiv   pre-print
In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation.  ...  This paper presents a novel framework to recover detailed avatar from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, texture, and viewpoints.  ...  [70] have proposed a multi-layer representation of garments and body to capture human performance using an RGBD camera.  ... 
arXiv:2108.02931v1 fatcat:66rbl5dhnvdsvbatfoo5znaabm

Photo-Realistic Facial Details Synthesis from Single Image [article]

Anpei Chen, Zhang Chen, Guli Zhang, Ziheng Zhang, Kenny Mitchell, Jingyi Yu
2019 arXiv   pre-print
We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details.  ...  For geometry, we capture 366 high-quality 3D scans from 122 different subjects under 3 facial expressions.  ...  ., captured by RGBD cameras [12] . More extensive facial databases have been recently made publicly available [58, 24, 55, 30, 7] , with an emphasis on handling complex expressions [30, 7] .  ... 
arXiv:1903.10873v5 fatcat:kreeibindffllagj2aildo6e3a

Neural Re-Rendering of Humans from a Single Image [article]

Kripasindhu Sarkar, Dushyant Mehta, Weipeng Xu, Vladislav Golyanik, Christian Theobalt
2021 arXiv   pre-print
Human re-rendering from a single image is a starkly under-constrained problem, and state-of-the-art algorithms often exhibit undesired artefacts, such as over-smoothing, unrealistic distortions of the  ...  Our algorithm represents body pose and shape as a parametric mesh which can be reconstructed from a single image and easily reposed.  ...  Neural Re-Rendering of Humans from a Single Image  ... 
arXiv:2101.04104v1 fatcat:6snujhlbpbgd7nc4gcw62soivy

Recovering 3D Human Mesh from Monocular Images: A Survey [article]

Yating Tian, Hongwen Zhang, Yebin Liu, Limin Wang
2022 arXiv   pre-print
Estimating human pose and shape from monocular images is a long-standing problem in computer vision.  ...  To the best of our knowledge, this is the first survey to focus on the task of monocular 3D human mesh recovery.  ...  ZJU-MoCap [35] consists of 9 dynamic human sequences captured by 21 synchronized cameras in a multi-view setup.  ... 
arXiv:2203.01923v2 fatcat:vb6xa5wdsrhdxd2ebvg54qq2m4

Data-Driven Shape Analysis and Processing [article]

Kai Xu, Vladimir G. Kim, Qixing Huang, Evangelos Kalogerakis
2015 arXiv   pre-print
In contrast to traditional approaches, a key feature of data-driven approaches is that they aggregate information from a collection of shapes to improve the analysis and processing of individual shapes  ...  In addition, they are able to learn models that reason about properties and relationships of shapes without relying on hard-coded rules or explicitly programmed instructions.  ...  Finally, the popularity of commodity RGBD cameras has significantly simplified the acquisition of indoor scenes.  ... 
arXiv:1502.06686v1 fatcat:upajios4y5a6dgf2zw7faqai4a

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 5431-5446 Learning a Single Model With a Wide Range of Quality Factors for JPEG Image Artifacts Removal.  ...  Verma, M., +, TIP 2020 1618-1627 Learning a Single Model With a Wide Range of Quality Factors for JPEG Image Artifacts Removal.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m
« Previous Showing results 1 — 15 out of 56 results