[SIST Seminar] Object-Compositional Neural Implicit Surfaces

ON2024-01-18TAG: ShanghaiTech UniversityCATEGORY: Lecture

Topic: Object-Compositional Neural Implicit Surfaces

Speaker: Professor CAI Jianfei, Faculty of IT, Monash University

Date and time: 15:00–16:00, January 24

Venue: SIST 1A-200

Host: GAO Shenghua


Abstract:

Neural Radiance Fields (NeRF) has been a major paradigm for 3D representation, providing implicit shape information and view-dependent appearance simultaneously. Based on this new representation, seminal 3D generation approaches have been proposed that aim to generate photorealistic images from a given distribution in a 3D-aware and view-consistent manner, while their performance in 3D geometry reconstruction is limited. On the other hand, several works demonstrate that rendering neural implicit surfaces, where gradients are concentrated around surface regions, is able to produce a high-quality 3D reconstruction. However, they focus only on holistic scene representation yet ignore individual objects inside it, thus limiting potential downstream applications. In this talk, we wilI first present our work, ObjectSDF, which provides a nice object-compositional neural implicit surfaces framework that can jointly reconstruct the scene and objects inside it with only semantic masks. We will also introduce its improved version, ObjectSDF++, which further enhances ObjectSDF in terms of quality and efficiency. CAI Jianfei is a Professor at Faculty of IT, Monash University, where he had served as the inaugural Head for the Data Science & Al Department. Before that, he was Head of Visual and Interactive Computing Division and Head of Computer Communications Division in Nanyang Technological University (NTU). His major research interests include computer vision, deep learning and multimedia.