Welcome to my GitHub profile! I'm a passionate researcher and developer with a keen interest in Computer Vision, Deep Learning, and 3D Scene Flow. Here's a bit more about me:
- Computer Vision: Image recognition, image generation, video captioning.
- World Models: Model-based automatic driving scene generation.
- 2D/3D Object Detection: Pure vision, pure LiDAR, and 2D-3D fusion deep learning algorithms.
- Deep Learning on Point Clouds: Feature extraction, matching and fusion, graph network.
- 3D Scene Flow: Unsupervised learning, point cloud processing.
- LiDAR Odometry: Large-scale point cloud registration, motion estimation.
A novel framework for 4D point cloud interpolation using Gaussian processes. Accepted at NeurIPS 2024.
An advanced 3D scene flow labelling tool designed for complex environments. Accepted at CVPR 2024.
A comprehensive solution for 3D scene flow prediction and labelling. Published in TII 2022.
A GAN-based framework for super-resolution and flow estimation in 3D scenes. Published in AIS 2022.
Check out my Google Scholar profile for a full list of my publications: Google Scholar
- Email: [email protected]
- Personal Website: jiangchaokang.github.io
- Google Scholar: Jiang Chaokang
I'm always looking to expand my skill set. Currently, I'm diving deeper into:
- Advanced techniques in 3D point cloud processing.
- Enhancing model accuracy for automatic driving scenes.
- Exploring new architectures in deep learning for computer vision.
- I love contributing to open-source projects.
- In my free time, you can find me exploring new hiking trails.
- I'm a coffee enthusiast βοΈ.