Datasets › ScanNet++

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

archive 2025-07-28

ScanNet++ is a large scale dataset with 450+ 3D indoor scenes containing sub-millimeter resolution laser scans, registered 33-megapixel DSLR images, and commodity RGB-D streams from iPhone. The 3D reconstructions are annotated with long-tail and label-ambiguous semantics to benchmark semantic understanding methods, while the coupled DSLR and iPhone captures enable benchmarking of novel view synthesis methods in high-quality and commodity settings.

Benchmarks archive 2025-07-28

All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

21 shown of 21 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 25. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
3DGEER: Exact and Efficient Volumetric Rendering with 3D Gaussians 1 1 29 May 2025 not harvested
Cross-modal feature fusion for robust point cloud registration with ambiguous geometry 1 1 19 May 2025 not harvested
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation 1 1 24 Mar 2025 not harvested
Sonata: Self-Supervised Learning of Reliable Point Representations 2 1 20 Mar 2025 ran 5 of 19 samples (14 unverified)
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting 1 1 17 Dec 2024 ran 2 of 2 samples (0 unverified)
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking 0 1 25 Nov 2024 not harvested
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis 0 1 2 Oct 2024 not harvested
Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras 0 1 7 Sep 2024 not harvested
UniDet3D: Multi-dataset Indoor 3D Object Detection 1 1 6 Sep 2024 not harvested
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation 1 1 21 Mar 2024 not harvested
SAI3D: Segment Any Instance in 3D Scenes 0 1 17 Dec 2023 not harvested
Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance 1 1 17 Dec 2023 ran 8 of 8 samples (0 unverified)
Point Transformer V3: Simpler, Faster, Stronger 3 1 15 Dec 2023 ran 7 of 11 samples (4 unverified)
OctFormer: Octree-based Transformers for 3D Point Clouds 4 1 4 May 2023 ran 2 of 9 samples (7 unverified)
Learning Context-aware Classifier for Semantic Segmentation 2 1 21 Mar 2023 ran 3 of 5 samples (2 unverified)
TR3D: Towards Real-Time Indoor 3D Object Detection 0 1 6 Feb 2023 not harvested
Point Transformer V2: Grouped Vector Attention and Partition-based Pooling 2 1 11 Oct 2022 not harvested
Geometric Transformer for Fast and Robust Point Cloud Registration 2 1 14 Feb 2022 ran 4 of 9 samples (5 unverified; 9 pointer-only for licence)
FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection 2 1 1 Dec 2021 not harvested
PREDATOR: Registration of 3D Point Clouds with Low Overlap 5 1 25 Nov 2020 ran 0 of 1 samples (1 unverified; 1 pointer-only for licence)
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks 8 1 18 Apr 2019 ran 1 of 2 samples (1 unverified; 2 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • ScanNet++
  • ScanNet++ (trained on 3DMatch)

2 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections