A procedural Blender pipeline for photorealistic training image generation

Autonomous UAV Navigation without Collision using Visual Information in Airsim

ForkNet: Adversarial Semantic Scene Completion from a Single Depth Image - ICCV 2019

A tutorial on stereoscopic depth maps, focusing on triangulation and rectification

Synthetic Blender Dataset Production

A real-time depth filling approach based on prior image segmentation (http://www.atapour.co.uk/papers/BMVC2017.pdf).

3D Object Detection (iHack IIT Bombay) - Deep Learning based real-Time solution using YOLO and Fast RCNN

DeepDoors2 is a dataset for 2D/3D door classification, 2D door detection and 2D door segmentation.

Inference demo and evaluation scripts for the MICCAI-2019 paper "Human Pose Estimation on Privacy-Preserving Low-Resolution Depth Images"

Remote Color Depth Camera without any 3rd-party dependencies in iOS.

Repository for the implementation of "FastV2C-HandNet: Fast Voxel to Coordinate Hand Pose Estimation with 3D Convolutional Neural Networks"

ANALYSIS OF A ROBUST EDGE DETECTION SYSTEM IN DIFFERENT COLOR SPACES USING COLOR AND DEPTH IMAGES

semillero computer vision

A SPATIAL AND FREQUENCY BASED METHOD FOR MICRO FACIAL EXPRESSIONS RECOGNITION USING COLOR AND DEPTH IMAGES

A data set for upper body orientation estimation of humans with continuous ground truth labels for the angle perpendicular to the ground

Conversion of depth data to derived images that allow classical feature detection. My master thesis.

Major project on Hand sign classification using RGB-D camera (primesense). Classification done based on depth images, rgb images and depth information seperately.

[TCYB2018] Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images

Dataset for patch-based person classification (person vs. non-person objects) and posture classification (standing vs. sitting vs. squatting). The data was recorded using a Kinect2 sensor and consists of labeled depth image patches of 27 persons in various postures and of various non-person objects. In total, the dataset consists of more than 23…