I'm a Ph.D. Candidate in Computer Science at the University of Minnesota - Twin Cities, working at the intersection of Computer Vision, 3D Vision, and Neuroscience. My research focuses on developing self-supervised frameworks for 3D motion prediction, markerless pose estimation, and understanding the neural correlates of freely moving subjects.
- Prototyping a third-person narrative game (Aghori) with Unreal Engine, simulating supernatural combat and dynamic particle systems using C++ and Python.
- Designing a video-to-3D pipeline for environmental reconstruction using Gaussian Splatting and COLMAP.
- Automating geometric constraint detection for parametric CAD using Computer Vision and Deep Learning.
- Researching 3D pose generation with latent diffusion models (ControlNet) from multimodal data.
- Languages: Python, C++, MATLAB, JavaScript
- ML Frameworks: PyTorch, TensorFlow, OpenCV, Keras
- Domains: 3D Reconstruction, Pose Estimation, Diffusion Models, Domain Adaptation
- Graphics & Systems: OpenGL, CUDA, Blender, Unreal Engine, SolidWorks API
- MLOps: Docker, CI/CD, Git
- OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates (IJCV '23)
- Self-supervised Secondary Landmark Detection via 3D Representation Learning (IJCV '23)
- Automated Markerless Pose Estimation in Freely Moving Macaques (Nature Communications '20)
Feel free to explore my repositories below. If you'd like to collaborate or chat about 3D Vision, generative AI, or neuroengineering, feel free to reach out via LinkedIn or email!