The Replica Dataset: A Digital Replica of Indoor Spaces
This dataset addresses the need for visually, geometrically, and semantically realistic indoor environments for ML researchers, potentially enabling better transfer to real-world data, though it is incremental as it builds on existing dataset efforts.
The authors introduced Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions with detailed geometric, semantic, and reflective properties, aiming to support machine learning research in areas like computer vision and embodied agents by providing realistic generative models.
We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale. Each scene consists of a dense mesh, high-resolution high-dynamic-range (HDR) textures, per-primitive semantic class and instance information, and planar mirror and glass reflectors. The goal of Replica is to enable machine learning (ML) research that relies on visually, geometrically, and semantically realistic generative models of the world - for instance, egocentric computer vision, semantic segmentation in 2D and 3D, geometric inference, and the development of embodied agents (virtual robots) performing navigation, instruction following, and question answering. Due to the high level of realism of the renderings from Replica, there is hope that ML systems trained on Replica may transfer directly to real world image and video data. Together with the data, we are releasing a minimal C++ SDK as a starting point for working with the Replica dataset. In addition, Replica is `Habitat-compatible', i.e. can be natively used with AI Habitat for training and testing embodied agents.