Reality Capture and Digital Twins

ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

Chandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner, Angela Dai

Published 2023-08-22

Thumbnail for ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes
📄 Paper🌐 Project💻 Code🎥 Video
We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a high-end laser scanner at sub-millimeter resolution, along with registered 33-megapixel images from a DSLR camera, and RGB-D streams from an iPhone. Scene reconstructions are further annotated with an open vocabulary of semantics, with label-ambiguous scenarios explicitly annotated for comprehensive semantic understanding. ScanNet++ enables a new real-world benchmark for novel view synthesis, both from high-quality RGB capture, and importantly also from commodity-level images, in addition to a new benchmark for 3D semantic scene understanding that comprehensively encapsulates diverse and ambiguous semantic labeling scenarios. Currently, ScanNet++ contains 460 scenes, 280,000 captured DSLR images, and over 3.7M iPhone RGBD frames.

Abstract

We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a high-end laser scanner at sub-millimeter resolution, along with registered 33-megapixel images from a DSLR camera, and RGB-D streams from an iPhone. Scene reconstructions are further annotated with an open vocabulary of semantics, with label-ambiguous scenarios explicitly annotated for comprehensive semantic understanding. ScanNet++ enables a new real-world benchmark for novel view synthesis, both from high-quality RGB capture, and importantly also from commodity-level images, in addition to a new benchmark for 3D semantic scene understanding that comprehensively encapsulates diverse and ambiguous semantic labeling scenarios. Currently, ScanNet++ contains 460 scenes, 280,000 captured DSLR images, and over 3.7M iPhone RGBD frames.

Topics

2D floor plan3D Reconstruction3D floor plan3DGSBIMDatasetFloor Plan Reconstruction and ParametrizationLiDARNeRFReview PaperSLAMSfMdigital twinsimage-to-planindoor scene reconstructionlayout recoverymesh-to-BIMobject detectionparametric BIMphotogrammetrypoint cloudspoint-cloud-to-planroom segmentationscan-to-BIMscene editingscene interactionscene understandingsemantic segmentationstructural element detection

Cite this paper

@misc{yeshwanth2023scannet,
  title = {ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes},
  author = {Chandan Yeshwanth and Yueh-Cheng Liu and Matthias Nießner and Angela Dai},
  year = {2023},
  eprint = {2308.11417},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.11417}
}