SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth

TL;DR

SceneNet RGB-D is a large-scale synthetic dataset of 5 million photorealistic indoor RGB-D images with ground truth, designed to advance scene understanding and geometric vision research.

Contribution

It introduces a vast, diverse synthetic dataset with accurate ground truth for training and evaluating indoor scene understanding and geometric computer vision algorithms.

Findings

Provides a large-scale dataset suitable for pre-training deep models.

Enables research on 3D scene labeling with perfect camera and depth data.

Facilitates development of data-driven methods for indoor scene understanding.

Abstract

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection, and also for geometric computer vision problems such as optical flow, depth estimation, camera pose estimation, and 3D reconstruction. Random sampling permits virtually unlimited scene configurations, and here we provide a set of 5M rendered RGB-D images from over 15K trajectories in synthetic layouts with random but physically simulated object poses. Each layout also has random lighting, camera trajectories, and textures. The scale of this dataset is well suited for pre-training data-driven computer vision techniques from scratch with RGB-D inputs, which previously has been limited by relatively small labelled datasets in NYUv2 and SUN RGB-D. It also provides a basis for investigating 3D scene labelling tasks by providing perfect camera poses and depth data as proxy for a SLAM system. We host the dataset at http://robotvault.bitbucket.io/scenenet-rgbd.html