4 papers
A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
Wentao Qu, Guofeng Mei, Yang Wu +3
Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient tra…
LAHNet: Local Attentive Hashing Network for Point Cloud Registration
Wentao Qu, Xiaoshui Huang, Liang Xiao
Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a…
Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusion
Wentao Qu, Guofeng Mei, Jing Wang +3
Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trai…
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Wentao Qu, Jing Wang, YongShun Gong +2
Existing conditional Denoising Diffusion Probabilistic Models (DDPMs) with a Noise-Conditional Framework (NCF) remain challenging for 3D scene understanding tasks, as the complex g…