-
Keio University
- Yokohama, Japan
- https://chakio.github.io/Portfolio/
- https://orcid.org/0000-0002-3076-3258
Highlights
- Pro
Stars
USB camera driver based on ros_control
Encoding/decoding image transport for ROS. Only supports decoding H.264 for now.
Faster Whisper transcription with CTranslate2
YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
Gazebo simulator plugin to automatically generate a 2D occupancy map from the simulated world at a given height.
ROS Camera driver for GStreamer-based video streams.
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package
ImMesh: An Immediate LiDAR Localization and Meshing Framework
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
FILM: Frame Interpolation for Large Motion, In ECCV 2022.
pointcloud2gazebo is a package that allows you to create a Gazebo World from a 3D point cloud.
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
A LiDAR-Inertial localization package based on FAST-LIO2, operating with a known prior map.
[RAL 2023] A globally consistent LiDAR map optimization module
A ROS software package for maintaining and exchanging articulation models