The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.

Matlab Implementation of a 3D Reconstruction algorithm

IROS'16/IJRR "Sparse Sensing for Resource-Constrained Depth Reconstruction"

Robust Depth Estimation for Light Field via Spinning Parallelogram Operator

CVPR2018 - scene parsing network regulated by geometric prior

The official implementations for the "Zero-shot Depth Estimation From Light Field Using A Convolutional Neural Network" TCI2020, and "Unsupervised Depth Estimation from Light Field Using a Convolutional Neural Network" 3DV2018.

Matlab code for 3D face reconstruction from stereo image pairs

Integrated Imaging and Communication with Reconfigurable Intelligent Surfaces

😄Blur background using depth map and color image.

Fast cost volume post-processing for increased depth prediction in light-field imagery

Project Repository of the course "EE 702: Computer Vision"

Reconfigurable Intelligent Surface Aided Wireless Sensing for Scene Depth Estimation

In this repository, 8-point algorithm is used to find the fundamental matrix based on SVD. Disparity map is generated from left and right images. In addition, RealSense depth camera 435i is used to estimate object center depth. Image thresholding and object detection are implemented. It is apart of Assignment3 in Sensing, Perception and Actuatio…

Software to evaluate depth estimation of ZED and ZED Mini stereo cameras for measurement purposes as part of the Master Thesis Project: Sparse Stereo Visual Odometry with Local Non-Linear Least-Squares Optimization for Navigation of Autonomous Vehicles

Matlab script to estimate depth from stereo image pairs, using block-matching.

Sparse and Dense 3D Reconstruction

This repository contains my assignment solution for the Convex Optimization course (430.709A_001) offered by Seoul National University (Fall 2018).

Dense Disparity Map Estimation using Stereo Cameras