-
Inha university
- Republic of Korea, Incheon
Lists (16)
Sort Name ascending (A-Z)
Stars
[ICRA 2026] STONE Dataset: A Scalable Multi-Modal Surround-View 3D Traversability Dataset for Off-Road Robot Navigation
[AAAI 2025]Text to Point Cloud Localization with Multi-Level Negative Contrastive Learning
Official repository of Utonia: Toward One Encoder for All Point Clouds
A fast and robust point cloud registration library
A standalone C++17 grid map library for robotics — no ROS, just Eigen
🌐 A Roadmap for 3D Scene Understanding in the Wild
MCAP is a modular, performant, and serialization-agnostic container file format, useful for pub/sub and robotics applications.
Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving
Uses SAM3 to transfer 2D semantics onto 3D point clouds, producing segmented training data and efficient scene graphs for indoor environments.
ROS2 adapters for the Cross-Platform Production-ready C++ inference engine for YOLO models (v5-v12, YOLO26). Unified API for detection, segmentation, pose estimation, OBB, and classification. Built…
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes
Nav2 costmap layer for semantic segmentation
Deploying a quadruped robot policy(DreamWaQ, walk-these-ways, HIMLoco) trained in Isaacgym to ROS2 Gazebo for Sim-to-Sim
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Perception-aware multi-sensor fusion for 3D LiDAR semantic segmentation (ICCV 2021)
Visualize ROS topics inside a terminal with Unicode/ASCII art
A visual URDF editor that does not depend on ROS.
GEM: Online Globally consistent dense elevation mapping for unstructured terrain.
[RA-L 2026] R-VoxelMap: Accurate Voxel Mapping with Recursive Plane Fitting for Online LiDAR Odometry
Official implementation of "Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance"
A relocalization package for Livox LiDARs.
[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation
Physics-aware LiDAR degradation framework for SLAM robustness on real sensor data (Livox Avia/Mid-360 & Ouster)
[CVPR 2025 Highlight] Towards Autonomous Micromobility through Scalable Urban Simulation