44 citations · 191 across the 34 of their papers we have counts for
34 papers
Preserving Topological and Geometric Embeddings for Point Cloud Recovery
Kaiyue Zhou, Zelong Tan, Hongxiao Wang +2
Recovering point clouds involves the sequential process of sampling and restoration, yet existing methods struggle to effectively leverage both topological and geometric attributes…
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
Zhenyu Wang, Yali Li, Hengshuang Zhao +1
The current trend in computer vision is to utilize one universal model to address all various tasks. Achieving such a universal model inevitably requires incorporating multi-domain…
Dynamic Object Queries for Transformer-based Incremental Object Detection
Jichuan Zhang, Wei Li, Shuang Cheng +2
Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annot…
Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond
Jichuan Zhang, Yali Li, Xin Liu +1
Non-exemplar class-incremental learning (NECIL) is to resist catastrophic forgetting without saving old class samples. Prior methodologies generally employ simple rules to generate…
Map Optical Properties to Subwavelength Structures Directly via a Diffusion Model
Shijie Rao, Kaiyu Cui, Yidong Huang +6
Subwavelength photonic structures and metamaterials provide revolutionary approaches for controlling light. The inverse design methods proposed for these subwavelength structures a…
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation
Zhenyu Wang, Yali Li, Taichi Liu +2
In the current state of 3D object detection research, the severe scarcity of annotated 3D data, substantial disparities across different data modalities, and the absence of a unifi…