-
The Hong Kong Polytechnic University
- Hong Kong, China
- https://huaiyuanxu.github.io/
Highlights
- Pro
Stars
[ICCV2025] CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception
Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges
[ICLR2025] OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework
[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide
The official implementation of the RAL paper.
A curated list of awesome LLM/VLM/VLA for Autonomous Driving(LLM4AD) resources (continually updated)
A Survey of Embodied Learning for Object-Centric Robotic Manipulation
Multimodaler Anomalie-Detektions Benchmark für simulierte Szenarien
[Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
This repository will be posting analytic continual learning series, including Analytic Class-Incremental Learning (ACIL), Gaussian Kernel Embedded Analytic Learning (GKEAL), Dual-Stream Analytic Le…
[IEEE T-PAMI 2023] Awesome BEV perception research and cookbook for all level audience in autonomous diriving
Single Underwater Image Restoration Using Adaptive Attenuation-Curve Prior
Official implement of CVPR2023 ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
A repository for LiDAR 3D semantic segmentation in autonomous driving scenarios. Also the official implementations of our ECCV 2022 paper (SDSeg3D) and CVPR 2023 paper (MSeg3D).
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
Awesome-Remote-Sensing-Vision-Language-Models
Python partial re-implementation of accumuLaser in python from the KITTI360 devkits to recover label of individual pointclouds from aggregated pointclouds.
[ICCV 2023] GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation
[RA-L 2022, S2G2: Semi-Supervised Semantic Bird-Eye-View Grid-Map Generation using a Monocular Camera for Autonomous Driving]
[TCSVT] CorrI2P: Deep Image-to-Point Cloud Registration via Dense CorrespondenceThe code of CorrI2P