Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Bouaziz, Sofien"'
Autor:
Sun, Keqiang, Jourabloo, Amin, Bhalodia, Riddhish, Meshry, Moustafa, Rong, Yu, Yang, Zhengyu, Nguyen-Phuoc, Thu, Haene, Christian, Xu, Jiu, Johnson, Sam, Li, Hongsheng, Bouaziz, Sofien
Photo-realistic and controllable 3D avatars are crucial for various applications such as virtual and mixed reality (VR/MR), telepresence, gaming, and film production. Traditional methods for avatar creation often involve time-consuming scanning and r
Externí odkaz:
http://arxiv.org/abs/2408.13674
Autor:
Ranade, Siddhant, Lassner, Christoph, Li, Kai, Haene, Christian, Chen, Shen-Chi, Bazin, Jean-Charles, Bouaziz, Sofien
Neural Radiance Fields (NeRFs) encode the radiance in a scene parameterized by the scene's plenoptic function. This is achieved by using an MLP together with a mapping to a higher-dimensional space, and has been proven to capture scenes with a great
Externí odkaz:
http://arxiv.org/abs/2212.03406
Autor:
Chen, Zhang, Zhang, Yinda, Genova, Kyle, Fanello, Sean, Bouaziz, Sofien, Haene, Christian, Du, Ruofei, Keskin, Cem, Funkhouser, Thomas, Tang, Danhang
We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a h
Externí odkaz:
http://arxiv.org/abs/2109.05591
Autor:
Park, Keunhong, Sinha, Utkarsh, Hedman, Peter, Barron, Jonathan T., Bouaziz, Sofien, Goldman, Dan B, Martin-Brualla, Ricardo, Seitz, Steven M.
Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a learned def
Externí odkaz:
http://arxiv.org/abs/2106.13228
Autor:
Tan, Feitong, Tang, Danhang, Dou, Mingsong, Guo, Kaiwen, Pandey, Rohit, Keskin, Cem, Du, Ruofei, Sun, Deqing, Bouaziz, Sofien, Fanello, Sean, Tan, Ping, Zhang, Yinda
In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle la
Externí odkaz:
http://arxiv.org/abs/2103.15573
Autor:
Mishra, Shlok Kumar, Sengupta, Kuntal, Horowitz-Gelb, Max, Chu, Wen-Sheng, Bouaziz, Sofien, Jacobs, David
Publikováno v:
2022 IEEE international joint conference on biometrics (IJCB) (ORAL)
Presentation attack detection (PAD) is a critical component in secure face authentication. We present a PAD algorithm to distinguish face spoofs generated by a photograph of a subject from live images. Our method uses an image decomposition network t
Externí odkaz:
http://arxiv.org/abs/2103.12201
Autor:
Park, Keunhong, Sinha, Utkarsh, Barron, Jonathan T., Bouaziz, Sofien, Goldman, Dan B, Seitz, Steven M., Martin-Brualla, Ricardo
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones. Our approach augments neural radiance fields (NeRF) by optimizing an additional continuous volumetric
Externí odkaz:
http://arxiv.org/abs/2011.12948
Publikováno v:
European Conference on Computer Vision 2020
Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem. Inspired by billboards and geometric proxies used in computer graphics, this paper proposes Generative Latent Textured Objec
Externí odkaz:
http://arxiv.org/abs/2008.04852
Autor:
Tankovich, Vladimir, Häne, Christian, Zhang, Yinda, Kowdle, Adarsh, Fanello, Sean, Bouaziz, Sofien
This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a
Externí odkaz:
http://arxiv.org/abs/2007.12140
Autor:
Tang, Danhang, Singh, Saurabh, Chou, Philip A., Haene, Christian, Dou, Mingsong, Fanello, Sean, Taylor, Jonathan, Davidson, Philip, Guleryuz, Onur G., Zhang, Yinda, Izadi, Shahram, Tagliasacchi, Andrea, Bouaziz, Sofien, Keskin, Cem
We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network architecture trained end-to-end,
Externí odkaz:
http://arxiv.org/abs/2005.08877