</> Code with Papers by Syntology

Datasets › NYUv2

NYUv2 (NYU-Depth V2)

Introduced in Indoor Segmentation and Support Inference from RGBD Images1 Jan 2012 archive 2025-07-28

The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect. It features:

  • 1449 densely labeled pairs of aligned RGB and depth images
  • 464 new scenes taken from 3 cities
  • 407,024 new unlabeled frames
  • Each object is labeled with a class and an instance number. The dataset has several components:
  • Labeled: A subset of the video data accompanied by dense multi-class labels. This data has also been preprocessed to fill in missing depth labels.
  • Raw: The raw RGB, depth and accelerometer data as provided by the Kinect.
  • Toolbox: Useful functions for manipulating the data and labels.

Source: https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html Image Source: https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 16 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.

First row (archive order)PaperCode
Semantic Segmentation NYU Depth v2 OmniVec2 Mean IoU 63.6 OmniVec2 - A Novel Transformer based Network for Large... — 121 Compare
Monocular Depth Estimation NYU-Depth V2 HybridDepth absolute relative error 0.026 HybridDepth: Robust Metric Depth Fusion by Leveraging... cake-lab/hybriddepth 85 Compare
3D Semantic Scene Completion NYUv2 SG-SSC mIoU 55.4 2D Semantic-Guided Semantic Scene Completion aipixel/SG-SSC 28 Compare
Depth Estimation NYU-Depth V2 EVP RMS 0.224 EVP: Enhanced Visual Perception using Inverse... lavreniuk/evp 17 Compare
Real-Time Semantic Segmentation NYU Depth v2 AsymFormer mIoU 54.1 AsymFormer: Asymmetrical Cross-Modal Representation... Fourier7754/AsymFormer 10 Compare
Monocular Depth Estimation NYU-Depth V2 self-supervised IndoorDepth Root mean square error (RMSE) 0.494 Deeper into Self-Supervised Monocular Indoor Depth Estimation fcntes/indoordepth 8 Compare
3D Semantic Scene Completion from a single RGB image NYUv2 ISO mIoU 31.25 Monocular Occupancy Prediction for Scalable Indoor Scenes hongxiaoy/ISO 6 Compare
Surface Normals Estimation NYU Depth v2 Metric3Dv2(L, FT) % < 11.25 68.8 Metric3Dv2: A Versatile Monocular Geometric Foundation... yvanyin/metric3d 6 Compare
Boundary Detection NYU-Depth V2 InvPT odsF 78.1 InvPT: Inverted Pyramid Multi-task Transformer for Dense... prismformore/InvPT 3 Compare
Depth Completion NYU-Depth V2 NLSPN RMSE 0.092 Non-Local Spatial Propagation Network for Depth Completion zzangjinsun/NLSPN_ECCV20 3 Compare
Multi-Task Learning NYUv2 SwinMTL Mean IoU 58.14 SwinMTL: A Shared Architecture for Simultaneous Depth... pardistaghavi/swinmtl 2 Compare
Panoptic Segmentation NYU Depth v2 EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned) PQ 51.15 PanopticNDT: Efficient and Robust Panoptic Mapping tui-nicr/emsanet +3 2 Compare
3D Object Detection NYU Depth v2 SGPN-CNN MAP 41.3 SGPN: Similarity Group Proposal Network for 3D Point... laughtervv/SGPN 1 Compare
Instance Segmentation NYU Depth v2 SGPN-CNN mAP@0.5 30.5 SGPN: Similarity Group Proposal Network for 3D Point... laughtervv/SGPN 1 Compare
Scene Segmentation NYU Depth v2 Dilated FCN-2s RGB Mean IoU 32.3% Efficient Yet Deep Convolutional Neural Networks for... SharifAmit/DilatedFCNSegmentation 1 Compare
Surface Normals Estimation NYU-Depth V2 Surface Normals DSN RMSE 12.2 On Deep Learning Techniques to Boost Monocular Depth... — 1 Compare

Papers archive 2025-07-28

30 shown of 212 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 986. 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
DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization 0 1 26 May 2025 not harvested
HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework 1 1 18 Apr 2025 not harvested
DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation 1 3 7 Apr 2025 ran 0 of 3 samples (3 unverified)
UniK3D: Universal Camera Monocular 3D Estimation 1 1 20 Mar 2025 not harvested
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler 1 1 27 Feb 2025 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator 1 1 26 Feb 2025 not harvested
HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation 1 1 16 Jan 2025 not harvested
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation 1 1 5 Jan 2025 not harvested
Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer 0 1 23 Sep 2024 not harvested
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think 1 2 17 Sep 2024 ran 16 of 17 samples (1 unverified; 17 pointer-only for licence)
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion 0 1 15 Sep 2024 not harvested
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage 1 2 13 Sep 2024 ran 13 of 15 samples (2 unverified)
2D Semantic-Guided Semantic Scene Completion 1 1 12 Sep 2024 not harvested
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors 1 1 26 Jul 2024 ran 6 of 7 samples (1 unverified; 7 pointer-only for licence)
Monocular Occupancy Prediction for Scalable Indoor Scenes 1 1 16 Jul 2024 ran 4 of 9 samples (5 unverified)
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation 1 1 11 Jul 2024 not harvested
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer 1 4 3 Jun 2024 ran 7 of 10 samples (3 unverified)
HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion 1 1 4 Apr 2024 not harvested
UniDepth: Universal Monocular Metric Depth Estimation 3 1 27 Mar 2024 ran 15 of 26 samples (11 unverified; 25 pointer-only for licence)
ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation 1 1 27 Mar 2024 ran 11 of 15 samples (4 unverified; 15 pointer-only for licence)
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation 1 2 22 Mar 2024 ran 3 of 3 samples (0 unverified)
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation 0 1 19 Mar 2024 not harvested
SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images 1 2 15 Mar 2024 not harvested
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data 7 1 19 Jan 2024 ran 3 of 11 samples (8 unverified)
Context-Aware Interaction Network for RGB-T Semantic Segmentation 1 1 3 Jan 2024 not harvested
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning 0 1 1 Jan 2024 not harvested
Harnessing Diffusion Models for Visual Perception with Meta Prompts 1 1 22 Dec 2023 ran 4 of 6 samples (2 unverified)
Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model 0 1 20 Dec 2023 not harvested
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment 1 2 13 Dec 2023 not harvested
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation 4 1 4 Dec 2023 ran 14 of 26 samples (12 unverified)

The full list of 212 is in the JSON twin.

Dataset loaders archive 2025-07-28

huggingface.co/datasets/0jl/NYUv2huggingface/datasetstfpytorchjax
huggingface.co/datasets/sayakpaul/nyu_depth_v2huggingface/datasetstfpytorchjax
www.tensorflow.org/datasets/catalog/nyu_depth_v2tensorflow/datasetstfjax

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

Tasks archive 2025-07-28

Semantic SegmentationInstance Segmentation3D Object DetectionDepth EstimationPanoptic SegmentationMonocular Depth EstimationMulti-Task LearningScene SegmentationDepth CompletionBoundary DetectionReal-Time Semantic SegmentationSurface Normals Estimation3D Semantic Scene Completion3D Semantic Scene Completion from a single RGB imageSurface Normal EstimationScene Classification (unified classes)Plane Instance SegmentationZero-shot Scene Classification (unified classes)

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

RGB-D

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • NYU-Depth V2
  • NYU Depth v2
  • NYU-Depth V2 Surface Normals
  • NYUv2
  • NYU-Depth V2 self-supervised

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