collaborators

5 papers

cs.CV2024

OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

Yanmin Wu, Jiarui Meng, Haijie Li +8

This paper introduces OpenGaussian, a method based on 3D Gaussian Splatting (3DGS) capable of 3D point-level open vocabulary understanding. Our primary motivation stems from observ…

cs.CV2024

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior

Sen Yang, Minyue Jiang, Ziwei Fan +6

Recent advances in autonomous driving systems have shifted towards reducing reliance on high-definition maps (HDMaps) due to the huge costs of annotation and maintenance. Instead,…

cs.CV2024

Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection

Jiacheng Zhang, Jiaming Li, Xiangru Lin +6

We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D…

cs.CV2024

TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model

Jiazhi Guan, Quanwei Yang, Kaisiyuan Wang +9

Recently, 2D speaking avatars have increasingly participated in everyday scenarios due to the fast development of facial animation techniques. However, most existing works neglect…

cs.CV2024

MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction

Jing Yang, Minyue Jiang, Sen Yang +5

The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements. Current state-of-the-art methods often…