Filters








14 Hits in 7.0 sec

FaceCollage

Fuwen Tan, Chi-Wing Fu, Teng Deng, Jianfei Cai, Tat-Jen Cham
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
This paper presents FaceCollage, a robust and real-time system for head reconstruction that can be used to create easy-to-deploy telepresence systems, using a pair of consumer-grade RGBD cameras that provide  ...  A key feature is that the system is very simple to rapidly deploy, with autonomous calibration and requiring minimal intervention from the user, other than casually placing the cameras.  ...  Fu was supported by the Shenzhen Science and Technology Program (JCYJ20170413162617606).  ... 
doi:10.1145/3123266.3123281 dblp:conf/mm/TanFDCC17 fatcat:hlsmrwb66jggviwzoagmbpfose

Learning Dynamic View Synthesis With Few RGBD Cameras [article]

Shengze Wang, YoungJoong Kwon, Yuan Shen, Qian Zhang, Andrei State, Jia-Bin Huang, Henry Fuchs
2022 arXiv   pre-print
We propose to utilize RGBD cameras to remove these limitations and synthesize free-viewpoint videos of dynamic indoor scenes.  ...  We enforce spatial-temporal consistency via the proposed Cycle Reconstruction Consistency and Temporal Stabilization module to reduce these artifacts.  ...  We intend to improve both the speed and visual quality to enable real-time telepresence systems with commodity RGBD cameras for future work.  ... 
arXiv:2204.10477v2 fatcat:tfortvxrwrcthkcrnbxjdslf7y

Hybrid modelling of non-rigid scenes from RGBD cameras

Charles Malleson, Jean-Yves Guillemaut, Adrian Hilton
2018 IEEE transactions on circuits and systems for video technology (Print)  
The approach allows arbitrary dynamic scenes to be efficiently represented with temporally consistent structure and enhanced levels of detail and completeness where possible, but gracefully falls back  ...  Piecewise TSDF fusion (grid per part) Composite TSDF fusion (single grid combining parts) Textured 4D mesh (extracted from composite TSDF, animated with part motion) Residual depth maps (Sec.  ...  ACKNOWLEDGMENT This work was funded by the EU FP7 project SCENE and EPSRC Audio-Visual Media Platform Grant EP/PO22529/1.  ... 
doi:10.1109/tcsvt.2018.2863027 fatcat:ydefxrbxn5h75acnl33ektzv3u

Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translation [article]

Lingjie Liu, Weipeng Xu, Marc Habermann, Michael Zollhoefer, Florian Bernard, Hyeongwoo Kim, Wenping Wang, Christian Theobalt
2021 arXiv   pre-print
Given the pose information, the first CNN predicts a dynamic texture map that contains time-coherent high-frequency details, and the second CNN conditions the generation of the final video on the temporally  ...  In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of  ...  . • High-resolution video synthesis of humans with controllable target motions and temporally coherent fine-scale detail.  ... 
arXiv:2001.04947v3 fatcat:ppii2ilexze7nkejshrohlky4u

Neural Rendering and Reenactment of Human Actor Videos [article]

Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Hyeongwoo Kim, Florian Bernard, Marc Habermann, Wenping Wang, Christian Theobalt
2019 arXiv   pre-print
We propose a method for generating video-realistic animations of real humans under user control.  ...  With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models, and can also be used to realistically edit existing videos  ...  We also thank Liqian Ma for his great help with comparison; Franziska Mueller and Ikhsanul Habibie for data acquisition; Jiatao Gu for discussion.  ... 
arXiv:1809.03658v3 fatcat:ciqgsmd3vffbvj3tye474gpxre

High-quality video view interpolation using a layered representation

C. Lawrence Zitnick, Sing Bing Kang, Matthew Uyttendaele, Simon Winder, Richard Szeliski
2004 ACM SIGGRAPH 2004 Papers on - SIGGRAPH '04  
Once these video streams have been processed, we can synthesize any intermediate view between cameras at any time, with the potential for space-time manipulation.  ...  a) ⇒ (b) ⇐ (c) (d) Figure 1: A video view interpolation example: (a,c) synchronized frames from two different input cameras and (b) a virtual interpolated view.  ...  At most, two temporal and two spatial decoding steps are required to move forward in time.  ... 
doi:10.1145/1186562.1015766 fatcat:nlocq533qjenfoydo2nd5qciym

High-quality video view interpolation using a layered representation

C. Lawrence Zitnick, Sing Bing Kang, Matthew Uyttendaele, Simon Winder, Richard Szeliski
2004 ACM Transactions on Graphics  
Once these video streams have been processed, we can synthesize any intermediate view between cameras at any time, with the potential for space-time manipulation.  ...  a) ⇒ (b) ⇐ (c) (d) Figure 1: A video view interpolation example: (a,c) synchronized frames from two different input cameras and (b) a virtual interpolated view.  ...  At most, two temporal and two spatial decoding steps are required to move forward in time.  ... 
doi:10.1145/1015706.1015766 fatcat:yv6cfyni6jcsvlomen3vtz2tny

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
and in real-time.  ...  Some of the most exciting experiences that Metaverse promises to offer, for instance, live interactions with virtual characters in virtual environments, require real-time photo-realistic rendering. 3D  ...  For example, we demonstrate adjusting the color/texture of the clothing, casting spotlight shadows, synthesizing distance lighting falloffs, etc, all with temporal coherence and in real-time.  ... 
arXiv:2202.06088v1 fatcat:23qn5ffx6raglmp363hz5iizne

LIME: Live Intrinsic Material Estimation [article]

Abhimitra Meka, Maxim Maximov, Michael Zollhoefer, Avishek Chatterjee, Hans-Peter Seidel, Christian Richardt, Christian Theobalt
2018 arXiv   pre-print
We present the first end to end approach for real time material estimation for general object shapes with uniform material that only requires a single color image as input.  ...  In addition, we propose a novel highly efficient perceptual rendering loss that mimics real world image formation and obtains intermediate results even during run time.  ...  In ometry, albedo and motion reconstruction using a single RGBD Proceedings of the International Conference on Computer camera.  ... 
arXiv:1801.01075v2 fatcat:bxvrwkxkgnhq5owufhqwzgrfre

State of the Art of Audio- and Video-Based Solutions for AAL

Slavisa ALeksic, Michael Atanasov, Jean Calleja Agius, Kenneth Camilleri, Anto Čartolovni, Pau Climent-Pérez, Sara Colantonio, Stefania Cristina, Vladimir Despotovic, Hazım Kemal Ekenel, Ekrem Erakin, Francisco Florez-Revuelta (+27 others)
2022 Zenodo  
Indeed, cameras and microphones are far less obtrusive with respect to the hindrance other wearable sensors may cause to one's activities. In addition, a single [...]  ...  Moreover, they are conceived to be intelligent, to be able to learn and adapt to the requirements and requests of the assisted people, and to synchronise with their specific needs.  ...  A simple real-time human silhouette extraction algorithm has been used to extract features for training of the support vector machine.  ... 
doi:10.5281/zenodo.6390708 fatcat:6qfwqd2v2rhe5iuu5zgz77ay4i

Generative RGB-D Face Completion for Head-Mounted Display Removal

Nels Numan, Frank ter Haar, Pablo Cesar
2021 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)  
These sensors not only capture a collection of RGB data like conventional cameras do, but additionally record a depth value for each pixel.  ...  We formulated this problem as a joint RGB-D face image inpainting task and proposed a GAN-based coarse-to-fine architecture that is capable of simultaneously filling in the missing color and depth information  ...  Other works approach the problem by training models that attempt to minimize the difference between the surface normals of the completed depth image and its ground truth [45, 46] .  ... 
doi:10.1109/vrw52623.2021.00028 fatcat:sbcco2znvnhvfpq3crk2xlqlza

Learning Geometry, Appearance and Motion in the Wild

Zhengqi Li
2021
However, most previous techniques either require a multi-camera setup or assume that the underlying scene is static, i.e., that the appearance and geometry do not change over time.  ...  me to synthesize photo-realistic novel view in both space and time.  ...  As in the original work [399] , we simulate a moving monocular camera by extracting images sampled from each camera viewpoint at different time instances, and evaluate the result of view synthesis with  ... 
doi:10.7298/x53b-a512 fatcat:e5uee5uc2nbphg5bprkvkphdfa

Real-Time Generative Hand Modeling and Tracking

Anastasia Tkach
2018
With a single-camera RGBD setup, we are faced with incomplete data due to self-occlusions and high noise levels (see Figure 2 .2).  ...  With a single-camera RGBD setup, we are faced with incomplete data due to self-occlusions and high noise levels. Calibration challenges.  ...  Note how setting z n = x * n , P 0 n =Σ n−1 and R = Σ * n the measurement update equations coincide with Equation 4.10 for product of two Gaussians, showing how the inter-frame regression algorithm is  ... 
doi:10.5075/epfl-thesis-8573 fatcat:jdpz4q4vabhurdfpc6os745rxi

Dense semantic SLAM

Renato F. Salas-Moreno, Andrew Davison
2015
for robust real-time camera tracking that relies on a consistent map.  ...  Simultaneous Localisation and Mapping (SLAM) began as a technique to enable real-time robotic navigation on previously unexplored environments.  ...  Real-Time SLAM with Hand-Held Sensorsment.  ... 
doi:10.25560/24524 fatcat:jdmx36lo2fd6toedwzjlcnebnq