DIODE: A Dense Indoor and Outdoor DEpth Dataset

08/01/2019

∙

We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements. DIODE (Dense Indoor/Outdoor DEpth) is the first public dataset to include RGBD images of indoor and outdoor scenes obtained with one sensor suite. This is in contrast to existing datasets that focus on just one domain/scene type and employ different sensors, making generalization across domains difficult.

READ FULL TEXT

DIODE: A Dense Indoor and Outdoor DEpth Dataset

DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes

A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing

OmniHorizon: In-the-Wild Outdoors Depth and Normal Estimation from Synthetic Omnidirectional Dataset

A dataset of ant colonies motion trajectories in indoor and outdoor scenes for social cluster behavior study

Learning to Dehaze From Realistic Scene with A Fast Physics Based Dehazing Network

Deep attention-based classification network for robust depth prediction

Structure-From-Motion and RGBD Depth Fusion

DIODE: A Dense Indoor and Outdoor DEpth Dataset

Related Research

DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes

A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing

OmniHorizon: In-the-Wild Outdoors Depth and Normal Estimation from Synthetic Omnidirectional Dataset

A dataset of ant colonies motion trajectories in indoor and outdoor scenes for social cluster behavior study

Learning to Dehaze From Realistic Scene with A Fast Physics Based Dehazing Network

Deep attention-based classification network for robust depth prediction

Structure-From-Motion and RGBD Depth Fusion