#
lturing
Follow
Lists (3)
Starred repositories
SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Heterogeneous Robots
42
Updated Jun 27, 2024
Merge superpoint、lightglue、MixVPR into VINS-FUSION for loop closure with TensorRT
StreamHiFiGAN offers a HiFiGAN vocoder model optimized for streaming inference, providing real-time audio synthesis capabilities.
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the best existing method …
UniSpeech - Large Scale Self-Supervised Learning for Speech
Toolbox for quantitative trajectory evaluation of VO/VIO
ROS compatible package for object tracking based on SAM, Cutie, GroundingDINO, YOLO-World, VLPart and DEVA
YOLO-World + EfficientViT SAM
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
MTR: Motion Transformer with Global Intention Localization and Local Movement Refinement, NeurIPS 2022.
Real-Time 3D Semantic Reconstruction from 2D data
GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation
很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
[ICCV 2023] Official implementation of the paper "Neural Interactive Keypoint Detection"
Small-scale indoor table AR visual-inertial datasets with 6DoF groundtruth.
Inertial Measurement Unit (IMU) based full body tracker for Steam VR.
中国节假日、调休、补班日历，ICS格式，可供IPhone、Google Calendar、Outlook等客户端订阅，包含节假日API
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
[CVPR 2024] AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
An integrated SfM (Structure from Motion) and MVS (Multi-View Stereo) solution.
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation