🛠️ Prepare and analyze conversational datasets with ease using our toolbox for CSV operations, filtering, analysis, and seamless PostgreSQL integration.

Monocular Depth Estimation Toolbox and Benchmark. [Arxiv'24 ScaleDepth, TCSVT'24 Plane2Depth, TIP'24 Binsformer]

This project is a reimplementation of the paper “Depth Map Prediction from a Single Image using a Multi-Scale Deep Network” by Eigen et al., . The work explores how deep convolutional neural networks can infer dense depth maps from single RGB images an inherently ill-posed problem due to the lack of explicit depth information.

DepthHist: Depth Estimation Using Differentiable Histogram with SliceStitch Augmentation- Submitted on IEEE TCI

Single Image Depth Estimation using UNet architecture trained on NYU Depth V2 dataset. Predicts depth maps from RGB images using PyTorch.

Scripts for downloading popular depth estimation datasets, including KITTI, DIODE, SUNRGBD, and soon NYUv2 and Make3D. This tool helps automate the download and organization of RGB images and corresponding depth maps, crucial for deep learning and computer vision research

Depth perception model trained on NYU depth dataset

[ECCV 2024] Monocular Occupancy Prediction for Scalable Indoor Scenes

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

Towards Online Waypoint Generation for a Quadrotor Using Enhanced Monocular Depth Estimation.

Towards Online Waypoint Generation for a Quadrotor Using Enhanced Monocular Depth Estimation.

Depth estimation from RGB images using fully convolutional neural networks.

Depth estimation from RGB images using a DenseNet based deep model.

Python toolbox for the NYU Depth Dataset V2

Monocular depth estimation using ResNet18 encoder decoder

Towards Online Waypoint Generation for a Quadrotor Using Enhanced Monocular Depth Estimation.

Object detection method that can simultaneously estimate the positions and depth of the objects from images

[CVPR 2021] Monocular depth estimation using wavelets for efficiency

ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation (ICCV 2021)

This is the code for the work "Single image dehazing using improved cycleGAN" published in the Journal of Visual Communication and Image Representation.