Deeper Depth Prediction with Fully Convolutional Residual Networks (FCRN)

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]

Monocular Depth Prediction

ICRA 2018 "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image" (PyTorch Implementation)

🌊 Images to → 2.5D Parallax Effect Video. A Free and Open Source ImmersityAI alternative

official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"

PyTorch implementation of Deep Ordinal Regression Network for Monocular Depth Estimation

Official implementation of the paper: Behind the Scenes: Density Fields for Single View Reconstruction (CVPR 2023)

The code and data of DiverseDepth

Code for "DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion" (CVPR 2021)

[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance

[ECCV 2018]: T2Net: Synthetic-to-Realistic Translation for Depth Estimation Tasks

Enforcing Temporal Consistency in Video Depth Estimation, ICCV-W 2021.

Code for T-ITS paper "Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry" and for ICRA paper "Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks".

TriDepth: Triangular Patch-based Deep Depth Prediction [Kaneko+, ICCVW2019(oral)]

Monocular depth prediction with PyTorch

Quick lookup for BlendedMVS scenes