Rendering photorealistic and dynamically moving human heads is crucial f...
A good motion retargeting cannot be reached without reasonable considera...
Commonly used backbones for semantic segmentation, such as ResNet and
Sw...
Fast generation of high-quality 3D digital humans is important to a vast...
People may perform diverse gestures affected by various mental and physi...
We present a novel audio-driven facial animation approach that can gener...
Semantic segmentation has recently achieved notable advances by exploiti...
We present a large-scale facial UV-texture dataset that contains over 50...
We present a neural network-based system for long-term, multi-action hum...
Line clouds, though under-investigated in the previous work, potentially...
It is very challenging to accurately reconstruct sophisticated human geo...
Built upon the risk analysis methodology (presented in the part I paper)...
Transporting hazardous materials (hazmats) using tank cars has more
sign...
Reconstructing 3D geometry from unoriented point clouds can benefit
many...
The evaluation of 3D face reconstruction results typically relies on a r...
Recent segmentation methods, such as OCR and CPNet, utilizing "class lev...
We present a method for reconstructing accurate and consistent 3D hands ...
Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis
...
Generating conversational gestures from speech audio is challenging due ...
We present animatable neural radiance fields for detailed human avatar
c...
Reconstructing a 3D hand from a single-view RGB image is challenging due...
Accurate 3D reconstruction of the hand and object shape from a hand-obje...
Because of the powerful learning capability of deep neural networks, cou...
For crowded scenes, the accuracy of object-based computer vision methods...
Computer vision tasks often have side information available that is help...