iHub-Drishti

3D Computer Vision Understanding geometry and depth from images or sensor data (e.g., stereo vision, LiDAR, depth cameras) Point cloud processing (e.g., registration, segmentation) 3D reconstruction (building 3D models from 2D images) SLAM (Simultaneous Localization and Mapping) 3D object detection and pose estimation Tools: OpenCV, PCL (Point Cloud Library), Open3D, PyTorch3D, NVIDIA Kaolin, MeshLab Generative AI Generating new content (images, 3D shapes, textures, animations) Working with models like GANs, VAEs, Diffusion Models Text-to-3D (e.g., using techniques like DreamFusion, Gaussian Splatting) Generative text (LLMs) for processing 3D scene descriptions or interactive systems Tools: PyTorch, TensorFlow, Stable Diffusion, Blender Python APIs, NVIDIA Omniverse, HuggingFace Transformers