DIODE: A Dense Indoor and Outdoor DEpth Dataset

By Igor Vasiljevic, Nicholas I. Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter and 1 more. 2019

365 citations recorded by the source corpus.

We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements. DIODE (Dense Indoor/Outdoor DEpth) is the first public dataset to include RGBD images of indoor and outdoor scenes obtained with one sensor suite. This is in contrast to existing datasets that focus on just one domain/scene type and employ different sensors, making generalization across domains difficult. The dataset is available for download at this http URL

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, neutral): “This distribution is roughly consistent with existing indoor depth datasets [64, 70, 78], but is noticeably different from outdoor datasets [16, 23].”
Learning to Recover 3D Scene Shape from a Single Image (2020, methodology): “To evaluate the generalizability of our proposed depth prediction method, we take 9 datasets which are unseen during training, including YouTube3D [6], OASIS [7], NYU [34], KITTI [14], ScanNet [8], DIODE [36], ETH3D [33], Sintel [4], and iBims-1 [22].”
Pretraining is All You Need for Image-to-Image Translation (2022, methodology): “We use DIODE [48] that contains 25K training images and 770 test images with dense depth and normal maps.”
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (2024, background): “Please refer to the following pages for comprehensive qualitative results on six unseen test sets (Figure 5 for KITTI [18], Figure 6 for NYUv2 [54], Figure 7 for Sintel [7], Figure 8 for DDAD [20], Figure 9 for ETH3D [51], and Figure 10 for DIODE [59]).”
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (2023, neutral): “ETH3D [45] and DIODE [50] are two high-resolution datasets, both featuring depth maps derived from LiDAR sensor measurements.”
Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image (2023, methodology): “To evaluate our method’s robustness of metric recovery, we test on 8 zero-shot datasets, i.e. NYU, KITTI, DIODE (indoor and outdoor parts), ETH3D, iBims-1, NuScenes, and 7Scenes.”
Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, neutral): “Evaluation details for monocular depth and normal estimation: a) To demonstrate the robustness of our metric depth estimation method, we evaluate on 7 zero-shot benchmarks, including NYUv2, KITTI [107], ScanNet [108], NuScenes [109], iBIMS-1 [110], and DIODE [111] (both indoor and outdoor).”
UniDepth: Universal Monocular Metric Depth Estimation (2024, methodology): “More precisely, each method is tested on validation splits from SUN-RGBD [38] without NYU split, Diode Indoor [40] , IBims-1 [22], VOID [44] HAM-MER [21], ETH-3D [37], nuScenes [4], and DDAD [19] with split proposed in [34] and evaluated with official masks.”
SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection (2020, methodology): “In our experiments, we first evaluate the performance of our proposed SNE on the DIODE dataset [33], a public surface normal estimation dataset containing RGBD vision data of both indoor and outdoor scenarios.”
Depth Anything 3: Recovering the Visual Space from Any Views (2025, neutral): “We compare with state-of-the-art metric depth estimation methods, including DepthPro [7], Metric3D v2 [37], UniDepthv1 [65] and UniDepthv2 [66], on 5 benchmarks: NYUv2 [76], KITTI [25], ETH3D [72], . . . SUN-RGBD [81] and DIODE (indoor) [88].”
Adding Conditional Control to Text-to-Image Diffusion Models (2023, methodology): “We implement ControlNets with Stable Diffusion to test various conditions, including Canny Edge [11], Depth Map [68], Normal Map [86], M-LSD lines [24], HED soft edge [90], ADE20K segmentation [95], Openpose [12], and user sketches.”
Qwen-Image Technical Report (2025, neutral): “Depth Estimation Table 14 summarizes performance on five widely used datasets: NYUv2 (Nathan Sil-berman &Fergus, 2012), KITTI (Geiger et al., 2013), ScanNet (Dai et al., 2017), DIODE (Vasiljevic et al., 2019), and ETH3D (Schops et al., 2017).”
GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image (2024, methodology): “We assess our model’s efficacy across six zero-shot relative depth benchmarks, including NYUv2 [60], KITTI [13], ETH3D [55], Scan-Net [7], DIODE [64], and OmniObject3D [66].”