ROEVO: Robust Organized Edge Feature-based Visual Odometry Using RGB-D Cameras

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Model Predictive Online Monitoring of Dynamical Systems for Nested Signal Temporal Logic Specifications

Neural SLAM Evaluation Benchmark. [CVPR'23] Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM

Dexterous Grasping via Temporal Parametric Optimization and Contact Diffusion

Bringing Characters to Life with Computer Brains in Unity

CoSurfGS: Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction

hardware and software design of the 250mm autonomous drone

[SIGGRAPH 2024 & TOG]

Towards Robust Keypoint Detection and Tracking: A Fusion Approach with Event-Aligned Image Features

本人的科研经验

GPU高性能编程CUDA实战随书代码

Add built-in support for quaternions to numpy

Interpret numpy arrays as quaternionic arrays with numba acceleration

这是一款提高ChatGPT的数据安全能力和效率的插件。并且免费共享大量创新功能，如：自动刷新、保持活跃、数据安全、取消审计、克隆对话、言无不尽、净化页面、展示大屏、拦截跟踪、日新月异、明察秋毫等。让我们的AI体验无比安全、顺畅、丝滑、高效、简洁。

Plugin for the simulation of the Livox Mid-360

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

Implemented a pipeline for 2D image mosaic and stitching. Feature extraction & matching, Adaptive Non-Maximal Suppression (ANMS), geometric blur, RANSAC

Multi-level Wavelet-CNN for Image Restoration