(Chris) Wei Xun Lai's Projects
Collaboration between EECS 106a /206a and ROAR lab Starter code.
Using NumC, SimD, and Open MP methods to speed up matrix multiplication and such
Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems
An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch
My version of the autoware tracker and such to include more documentation, some from Chatgpt and others.
Official repository of Learning to Act from Actionless Videos through Dense Correspondences.
ROS1/2 Driver for AVT cameras using VIMBA SDK.
Experimentation on BLIP2
Checkerboard detector for Luminar AV24
Config files for my GitHub profile.
Competitive autoencoder to learn optimized feature filters for patterns
Material for cuda-mode lectures
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
PyTorch code and models for the DINOv2 self-supervised learning method.
[IEEE ICRA'23] A new lightweight LiDAR-inertial odometry algorithm with a novel coarse-to-fine approach in constructing continuous-time trajectories for precise motion correction.
A repository to distill DinoV2 into Resnet, MobileNetv2 given some existing dataset.
Creating a documentation for all the tools I've used across different platforms
DOE Trucks update
RGB Edge guided filter that is capable of also doing edge-preserving image smoothing
Doing the first project, creating trajectories and controllers
Final Project for UC Berkeley EECS149.
This is to test my git knowledge and test it with 2 users
The official implementation of "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Lidar-Camera calibration using homography to get the best apprximate intrinsic and extrinsic matrix
A simple repository with a pipeline to identify and extract important camera data to be labelled.
Extracts Desired ROS2 mcap bags
ROS2 Euclidean Clustering for Pointclouds after applying Lidar-camera Projection, with date filtered with a YOLO Bounding box