[CVPR'19] Dataset and code used in the research project Scan2CAD: Learning CAD Model Alignment in RGB-D Scans

Volumetric structures such as voxels and SDFs implemented in pytorch

Explore object recognition, segmentation, and how to process depth data from camera sensors to help a robot better understand and navigate its world.

Generate customized voxel representations of protein-ligand complexes using GPU.

Batch multidimensional indexing for pytorch

Object Detection pipeline implemented using the Voxel Grid and ROI based filtering, 3D RANSAC segmentation, Euclidean clustering based on KD-Tree, and bounding boxes, by processing Point Cloud data from LiDAR sensor.

A machine Learning project that turns a 2D images into 3D voxels using tensorflow implemented AutoEncoder

Point Cloud Library Tutorial with ROS

This project uses low-cost stereo cameras for 3D scene perception by generating disparity maps and applying clustering for segmentation. It also constructs voxel grids for visualizing spatial structure and object segmentation.

Repo du projet du cours IFT3150