CVAug 22, 2023

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

arXiv:2308.11417v1724 citationsh-index: 86
Originality Synthesis-oriented
AI Analysis

This dataset addresses the need for comprehensive benchmarks in novel view synthesis and 3D semantic scene understanding for researchers in computer vision and robotics, though it is incremental as it builds upon existing datasets like ScanNet.

The authors tackled the lack of high-fidelity 3D indoor scene datasets by introducing ScanNet++, which couples high-quality and commodity-level geometry and color captures, resulting in a dataset with 460 scenes, 280,000 DSLR images, and over 3.7 million iPhone RGB-D frames.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes