We are seeking a highly motivated and technically skilled intern to join our team, focusing on cutting-edge research in Generative AI and 3D Reconstruction and Rendering. In this role, you will work both independently and collaboratively with a dynamic team of researchers to design, develop, and validate an innovative 3D pipeline. The ideal candidate will be passionate about applying AI technologies to solve real-world problems in the context of 3D/4D content creation and autonomous systems.

Responsibilities:

• Innovate within generative AI to explore new approaches in 3D/4D content generation, including but not limited to prompt-guided 3D scene creation, and adaptive content manipulation for realistic 3D environments.
• Develop and enhance 3D/4D rendering techniques, integrating machine learning to improve the efficiency and quality of real-time rendering processes, particularly for complex visual scenarios.
• Build and optimize a multiview-based 3D reconstruction pipeline that supports real-time rendering, with a specific focus on applications in autonomous driving and dynamic environments.

Requirements:

• PhD or Master in Computer Science, Electrical Engineering, or a related field, with a focus on deep learning and computer graphics.
• Proficient in transformer, diffusion model, SAM/CLIP, 3DGS and related architectures.
• Publications at top tier conferences such as ICCV, ECCV, CVPR, ICLR, NeurIPS, SIGGRAPH, or similar high-impact venues.