-
Xiamen University
- beijing
- https://blog.csdn.net/shenshikexmu
Stars
Convolutional Neural Networks for Denoising Gyroscopes of Low-Cost IMUs
[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion
Implementations in C++ of the Patch Match Stereo algorithm presented in: PatchMatch Stereo - Stereo Matching with Slanted Support Windows
PatchMatchStereo,倾斜窗口经典,效果极佳,OpenMVS&Colmap稠密匹配算法。完整实现,代码规范,注释清晰,博客教学!
DeepSeek Coder: Let the Code Write Itself
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
Reproduce the content of the paper titled "openVins state initialization details and derivation"
Release repo for our SLAM Handbook
Java-based implementation of YAML IO support in MATLAB.
Implementation of Lucas-Kanade optical flow algorithm.
A Clash GUI based on tauri. Supports Windows, macOS and Linux.
An open source platform for visual-inertial navigation research.
Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Quaternion kinematics for the error-state Kalman filter 中文翻译版
A Robust and Versatile Monocular Visual-Inertial State Estimator
[CVPR2024] SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
A resource repository for 3D machine learning
Building a quick conversation-based search demo with Lepton AI.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
运动捕捉系统GLMocap包括多相机硬件开源方案和上位机软件算法方案的低成本运动捕捉系统。目前设计指标为低成本实现毫米级空间定位,辅助无人机等有室内定位需求的装置和设备。
[CVPR 2024] DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
Official code for ICCV 2023 paper: "TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering".