Výsledky vyhledávání - "3D from multi-view and sensors"

HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video Autor Weng, Chung-Yi, Curless, Brian, Srinivasan, Pratul P., Barron, Jonathan T., Kemelmacher-Shlizerman, Ira

“… a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 360-degree camera path for that particular frame and body pose…”
Získat plný text

RigNeRF: Fully Controllable Neural 3D Portraits Autor Athar, ShahRukh, Xu, Zexiang, Sunkavalli, Kalyan, Shechtman, Eli, Shu, Zhixin

“…Volumetric neural rendering methods, such as neural radiance fields (NeRFs), have enabled photo-realistic novel view synthesis. However, in their standard…”
Získat plný text

BEHAVE: Dataset and Method for Tracking Human Object Interactions Autor Bhatnagar, Bharat Lal, Xie, Xianghui, Petrov, Ilya A., Sminchisescu, Cristian, Theobalt, Christian, Pons-Moll, Gerard

“… record ~15k frames at 5 locations with 8 subjects performing a wide range of interactions with 20 common objects…”
Získat plný text

Structured Local Radiance Fields for Human Avatar Modeling Autor Zheng, Zerong, Huang, Han, Yu, Tao, Zhang, Hongwen, Guo, Yandong, Liu, Yebin

“…It is extremely challenging to create an animatable clothed human avatar from RGB videos, especially for loose clothes due to the difficulties in motion…”
Získat plný text

Hallucinated Neural Radiance Fields in the Wild Autor Chen, Xingyu, Zhang, Qi, Li, Xiaoyu, Chen, Yue, Feng, Ying, Wang, Xuan, Wang, Jue

“…Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated…”
Získat plný text

HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs Autor Zhao, Fuqiang, Yang, Wei, Zhang, Jiakai, Lin, Pei, Zhang, Yingliang, Yu, Jingyi, Xu, Lan

“… field for tackling dynamic motions. The raw Human-NeRF can already produce reasonable rendering on sparse video inputs of unseen subjects and camera settings…”
Získat plný text

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video Autor Jiang, Boyi, Hong, Yang, Bao, Hujun, Zhang, Juyong

“… Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject…”
Získat plný text

Instant Volumetric Head Avatars Autor Zielonka, Wojciech, Bolkart, Timo, Thies, Justus

“… Our pipeline is trained on a single monocular RGB portrait video that observes the subject under different expressions and views…”
Získat plný text

Virtual Elastic Objects Autor Chen, Hsiao-yu, Tretschk, Edith, Stuyck, Tuur, Kadlecek, Petr, Kavan, Ladislav, Vouga, Etienne, Lassner, Christoph

“…We present Virtual Elastic Objects (VEOs): virtual objects that not only look like their real-world counterparts but also behave like them, even when subject to novel interactions…”
Získat plný text

3D Moments from Near-Duplicate Photos Autor Wang, Qianqian, Li, Zhengqi, Salesin, David, Snavely, Noah, Curless, Brian, Kontkanen, Janne

“…, photos of moving subjects from similar viewpoints, common in people's photo collections…”
Získat plný text

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions Autor Zhang, Juze, Luo, Haimin, Yang, Hongdi, Xu, Xinru, Wu, Qianyang, Shi, Ye, Yu, Jingyi, Xu, Lan, Wang, Jingya

“… of ~71 M frames on 10 subjects interacting with 23 objects. To process the HODome dataset, we develop NeuralDome, a layer-wise neural processing pipeline tailored…”
Získat plný text

PersonNeRF : Personalized Reconstruction from Photo Collections Autor Weng, Chung-Yi, Srinivasan, Pratul P., Curless, Brian, Kemelmacher-Shlizerman, Ira

“…We present PersonNeRF, a method that takes a collection of photos of a subject (e.g. Roger Federer) captured across multiple years with arbitrary body poses…”
Získat plný text

High-Res Facial Appearance Capture from Polarized Smartphone Images Autor Azinovic, Dejan, Maury, Olivier, Hery, Christophe, Niebner, Matthias, Thies, Justus

“… Leveraging this setup, we capture the face of a subject with cross-polarized and parallel-polarized light…”
Získat plný text

Command-driven Articulated Object Understanding and Manipulation Autor Chu, Ruihang, Liu, Zhengzhe, Ye, Xiaoqing, Tan, Xiao, Qi, Xiaojuan, Fu, Chi-Wing, Jia, Jiaya

“… Beyond the existing work that focuses on inferring articulation structures, we further support manipulating articulated shapes to align them subject to simple command templates…”
Získat plný text

3D Shape Reconstruction of Semi-Transparent Worms Autor Ilett, Thomas P., Yuval, Omer, Ranner, Thomas, Cohen, Netta, Hogg, David C.

“…3D shape reconstruction typically requires identifying object features or textures in multiple images of a subject…”
Získat plný text