MegaScenes: Scene-Level View Synthesis at Scale
This addresses the lack of scene-level training data for novel view synthesis, benefiting vision and graphics applications, but is incremental as it builds on existing pose-conditioned diffusion models.
The paper tackles the problem of scene-level novel view synthesis by creating a large-scale dataset, MegaScenes, from Internet photos, and improves generation consistency in state-of-the-art methods, achieving validated effectiveness on in-the-wild scenes.
Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these methods are limited by the lack of scene-level training data. Common dataset choices either consist of isolated objects (Objaverse), or of object-centric scenes with limited pose distributions (DTU, CO3D). In this paper, we create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. Internet photos represent a scalable data source but come with challenges such as lighting and transient objects. We address these issues to further create a subset suitable for the task of NVS. Additionally, we analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency. Through extensive experiments, we validate the effectiveness of both our dataset and method on generating in-the-wild scenes. For details on the dataset and code, see our project page at https://megascenes.github.io.