Datasets › 2D-3D-S

2D-3D-S (2D-3D-Semantic)

Introduced by Iro Armeni et al. in Joint 2D-3D-Semantic Data for Indoor Scene Understanding1 Jan 2017 archive 2025-07-28

The 2D-3D-S dataset provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. It covers over 6,000 m2 collected in 6 large-scale indoor areas that originate from 3 different buildings. It contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360° equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learning models and potentially unsupervised approaches utilizing the regularities present in large-scale indoor spaces.

Source: https://github.com/alexsax/2D-3D-Semantics Image Source: https://github.com/alexsax/2D-3D-Semantics

Benchmarks archive 2025-07-28

All 6 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

30 shown of 42 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 147. 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
Single Frame Semantic Segmentation Using Multi-Modal Spherical Images 1 5 18 Aug 2023 not harvested
SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation 1 2 6 Jun 2023 ran 8 of 11 samples (3 unverified; 9 pointer-only for licence)
Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation 1 2 21 Apr 2023 not harvested
Interpolated SelectionConv for Spherical Images and Surfaces 1 1 18 Oct 2022 not harvested
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions 1 2 4 Oct 2022 not harvested
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation 1 1 7 Sep 2022 ran 1 of 13 samples (12 unverified)
SphereDepth: Panorama Depth Estimation from Spherical Domain 0 1 29 Aug 2022 not harvested
Neural Contourlet Network for Monocular 360 Depth Estimation 1 1 3 Aug 2022 not harvested
Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation 1 2 25 Jul 2022 not harvested
3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform 1 1 19 Jul 2022 ran 7 of 12 samples (5 unverified)
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation 0 2 6 Jul 2022 not harvested
HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model 0 1 11 Apr 2022 not harvested
PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation 1 2 17 Mar 2022 ran 0 of 7 samples (7 unverified)
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers 1 2 9 Mar 2022 ran 2 of 2 samples (0 unverified)
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion 1 1 2 Mar 2022 ran 6 of 8 samples (2 unverified)
Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation 1 5 2 Mar 2022 not harvested
GLPanoDepth: Global-to-Local Panoramic Depth Estimation 1 1 6 Feb 2022 ran 2 of 4 samples (2 unverified)
PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation 0 1 2 Feb 2022 not harvested
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation 1 1 29 Dec 2021 not harvested
Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning 1 1 22 Sep 2021 ran 1 of 4 samples (3 unverified)
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation 1 1 24 Aug 2021 ran 0 of 4 samples (4 unverified)
SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based Representation 0 1 19 Jun 2021 not harvested
OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas 0 1 19 Apr 2021 not harvested
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering 1 1 1 Apr 2021 ran 1 of 10 samples (9 unverified)
SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama 1 1 25 Mar 2021 not harvested
UniFuse: Unidirectional Fusion for 360° Panorama Depth Estimation 1 1 6 Feb 2021 not harvested
HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features 1 4 23 Nov 2020 not harvested
AtlantaNet: Inferring the 3D Indoor Layout from a Single 360(∘) Image beyond the Manhattan World Assumption 1 1 1 Aug 2020 not harvested
Spin-Weighted Spherical CNNs 2 1 18 Jun 2020 ran 3 of 4 samples (1 unverified)
Geometric Structure Based and Regularized Depth Estimation From 360 Indoor Imagery 0 1 1 Jun 2020 not harvested

The full list of 42 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • 2D-3D-S
  • Stanford2D3D
  • Stanford2D3D Panoramic
  • Stanford2D3D Panoramic - RGBD
  • Stanford2D3D - RGBD

5 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