DIODE: A Dense Indoor and Outdoor DEpth Dataset

Abstract

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. The dataset is available for download at http://diode-dataset.org

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Matterport3D: Learning from RGB-D Data in Indoor Environments
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• High Quality Monocular Depth Estimation via Transfer Learning

Cited by in corpus (19)

• SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
• Guided Depth Map Super-resolution: A Survey
• Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator
• P${}^2$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
• VisualEchoes: Spatial Image Representation Learning through Echolocation
• Bidirectional Attention Network for Monocular Depth Estimation
• Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
• Ground-aware Monocular 3D Object Detection for Autonomous Driving
• Multi-Task Self-Training for Learning General Representations
• Learning to Recover 3D Scene Shape from a Single Image
• SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction
• Attentive Feature Reuse for Multi Task Meta learning
• Single Image Reflection Removal with Physically-Based Training Images
• OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
• Topological Regularization for Dense Prediction
• SIG: A Synthetic Identity Generation Pipeline for Generating Evaluation Datasets for Face Recognition
• Outdoor inverse rendering from a single image using multiview self-supervision
• Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the masses