Nerf-editing: geometry editing of neural radiance fields

YJ Yuan, YT Sun, YK Lai, Y Ma… - Proceedings of the …, 2022 - openaccess.thecvf.com
Implicit neural rendering, especially Neural Radiance Field (NeRF), has shown great
potential in novel view synthesis of a scene. However, current NeRF-based methods cannot …

Skeleton-free pose transfer for stylized 3d characters

Z Liao, J Yang, J Saito, G Pons-Moll, Y Zhou - European Conference on …, 2022 - Springer
We present the first method that automatically transfers poses between stylized 3D
characters without skeletal rigging. In contrast to previous attempts to learn pose …

Interactive nerf geometry editing with shape priors

YJ Yuan, YT Sun, YK Lai, Y Ma, R Jia… - … on Pattern Analysis …, 2023 - ieeexplore.ieee.org
Neural Radiance Fields (NeRFs) have shown great potential for tasks like novel view
synthesis of static 3D scenes. Since NeRFs are trained on a large number of input images, it …

MeshCLIP: Efficient cross-modal information processing for 3D mesh data in zero/few-shot learning

Y Song, N Liang, Q Guo, J Dai, J Bai, F He - Information Processing & …, 2023 - Elsevier
Abstract Text, 2D, and 3D information are crucial information representations in modern
science and management disciplines. However, complex and irregular 3D data produce …

A revisit of shape editing techniques: From the geometric to the neural viewpoint

YJ Yuan, YK Lai, T Wu, L Gao, L Liu - Journal of Computer Science and …, 2021 - Springer
Abstract 3D shape editing is widely used in a range of applications such as movie
production, computer games and computer aided design. It is also a popular research topic …

TapMo: Shape-aware Motion Generation of Skeleton-free Characters

J Zhang, S Huang, Z Tu, X Chen, X Zhan, G Yu… - arXiv preprint arXiv …, 2023 - arxiv.org
Previous motion generation methods are limited to the pre-rigged 3D human model,
hindering their applications in the animation of various non-rigged characters. In this work …

Attwalk: Attentive cross-walks for deep mesh analysis

R Ben Izhak, A Lahav, A Tal - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Mesh representation by random walks has been shown to benefit deep learning.
Randomness is indeed a powerful concept. However, it comes with a price--some walks …

Lcollision: Fast generation of collision-free human poses using learned non-penetration constraints

Q Tan, Z Pan, D Manocha - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
We present LCollision, a learning-based method that synthesizes collision-free 3D human
poses. At the crux of our approach is a novel deep architecture that simultaneously decodes …

Research on fraud detection method based on heterogeneous graph representation learning

X Zheng, C Feng, Z Yin, J Zhang, H Shen - Electronics, 2023 - mdpi.com
Detecting fraudulent users in social networks could reduce online fraud and
telecommunication fraud cases, which is essential to protect the lives and properties of …

Unsupervised Representation Learning for Diverse Deformable Shape Collections

S Hahner, S Attaiki, J Garcke… - … Conference on 3D …, 2024 - ieeexplore.ieee.org
We introduce a novel learning-based method for encoding and manipulating 3D surface
meshes. Our method is specifically designed to create an interpretable embedding space for …