Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Zhang, Congyi"'
Autor:
Zhang, Congyi, Yang, Jinfan, Hedlin, Eric, Takikawa, Suzuran, Vining, Nicholas, Yi, Kwang Moo, Wang, Wenping, Sheffer, Alla
Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parame
Externí odkaz:
http://arxiv.org/abs/2409.06030
The recent success of pre-trained diffusion models unlocks the possibility of the automatic generation of textures for arbitrary 3D meshes in the wild. However, these models are trained in the screen space, while converting them to a multi-view consi
Externí odkaz:
http://arxiv.org/abs/2406.18539
Color smudge operations from digital painting software enable users to create natural shading effects in high-fidelity paintings by interactively mixing colors. To precisely control results in traditional painting software, users tend to organize fla
Externí odkaz:
http://arxiv.org/abs/2405.02759
Deducing the 3D face from a skull is an essential but challenging task in forensic science and archaeology. Existing methods for automated facial reconstruction yield inaccurate results, suffering from the non-determinative nature of the problem that
Externí odkaz:
http://arxiv.org/abs/2403.16207
Autor:
Lin, Guying, Yang, Lei, Liu, Yuan, Zhang, Congyi, Hou, Junhui, Jin, Xiaogang, Komura, Taku, Keyser, John, Wang, Wenping
Neural implicit fields, such as the neural signed distance field (SDF) of a shape, have emerged as a powerful representation for many applications, e.g., encoding a 3D shape and performing collision detection. Typically, implicit fields are encoded b
Externí odkaz:
http://arxiv.org/abs/2401.01391
Autor:
Yang, Lei, Liang, Yongqing, Li, Xin, Zhang, Congyi, Lin, Guying, Sheffer, Alla, Schaefer, Scott, Keyser, John, Wang, Wenping
The recent surge of utilizing deep neural networks for geometric processing and shape modeling has opened up exciting avenues. However, there is a conspicuous lack of research efforts on using powerful neural representations to extend the capabilitie
Externí odkaz:
http://arxiv.org/abs/2309.09911
Autor:
Zhang, Congyi, Lin, Guying, Yang, Lei, Li, Xin, Komura, Taku, Schaefer, Scott, Keyser, John, Wang, Wenping
We propose a method, named DualMesh-UDF, to extract a surface from unsigned distance functions (UDFs), encoded by neural networks, or neural UDFs. Neural UDFs are becoming increasingly popular for surface representation because of their versatility i
Externí odkaz:
http://arxiv.org/abs/2309.08878
Autor:
Lin, Guying, Yang, Lei, Zhang, Congyi, Pan, Hao, Ping, Yuhan, Wei, Guodong, Komura, Taku, Keyser, John, Wang, Wenping
Neural implicit representations are known to be more compact for depicting 3D shapes than traditional discrete representations. However, the neural representations tend to round sharp corners or edges and struggle to represent surfaces with open boun
Externí odkaz:
http://arxiv.org/abs/2308.13934
3D Morphable models of the human body capture variations among subjects and are useful in reconstruction and editing applications. Current dental models use an explicit mesh scene representation and model only the teeth, ignoring the gum. In this wor
Externí odkaz:
http://arxiv.org/abs/2211.11402
Autor:
Wang, Jiepeng, Zhang, Congyi, Wang, Peng, Li, Xin, Cobb, Peter J., Theobalt, Christian, Wang, Wenping
3D reconstruction techniques have widely been used for digital documentation of archaeological fragments. However, efficient digital capture of fragments remains as a challenge. In this work, we aim to develop a portable, high-throughput, and accurat
Externí odkaz:
http://arxiv.org/abs/2211.06897