Profile

Shoukang Hu is a research scientist at Sony AI. His main research interests include exploring multiple modalities to enhance the advancement of perception, reconstruction, and generation. His recent work has focused on human avatar creation and 4D content generation. He is also interested in statistical modeling and optimization algorithms.
Before joining Sony AI, Shoukang Hu was a research fellow at MMLab@NTU. He obtained his Ph.D. from The Chinese University of Hong Kong and his B.E. degree from the University of Electronic Science and Technology of China.
For more information, please visit his personal webpage (https://skhu101.github.io/).

Message

My role at Sony AI involves empowering Sony with AI-Generated Content, including human avatar creation and 4D content generation.

Publications

Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

AAAI, 2025
Junyoung Seo, Jisang Han, Jaewoo Jung, Siyoon Jin, Joungbin Lee, Takuya Narihira, Kazumi Fukuda, Takashi Shibuya, Donghoon Ahn, Shoukang Hu, Seungryong Kim*, Yuki Mitsufuji

We introduce Vid-CamEdit, a novel framework for video camera trajectory editing, enabling the re-synthesis of monocular videos along user-defined camera paths. This task is challenging due to its ill-posed nature and the limited multi-view video data for training. Traditiona…

GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping

NeurIPS, 2024
Junyoung Seo, Kazumi Fukuda, Takashi Shibuya, Takuya Narihira, Naoki Murata, Shoukang Hu, Chieh-Hsin Lai, Seungryong Kim*, Yuki Mitsufuji

Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image (T2I) models with monocular depth e…