Let's make pottery!
January 14, 2024
·
1 min read
Accurate completion of archaeological artifacts is a critical aspect in several archaeological studies, including documentation of variations in style, inference of chronological and ethnic groups, and trading routes trends, among many others. However, most available pottery is fragmented, leading to missing textural and morphological cues. To address these issues and support archaeologists in their work, we developed a 3D Autoencoder Generative Adversarial Network (3D AEGAN) with the provided framework.
Authors
Yuchao Jin
(he/him)
Undergraduate
Hi, I’m an undergraduate at Peking University, specifically within the School of EECS, where I major in Intelligent Science and Technology. I have a strong passion for Computer Vision, Multimodal LLMs, and Embodied AI. After exploring 3D Gaussian Splatting and reconstruction techniques, I have recently shifted my focus to Embodied AI, multimodality, and Reinforcement Learning. I’m always open to discussing ideas with like-minded people—feel free to reach out and connect!