Depth Estimation

The INRIA Dense Light Field Dataset (DLFD) is a dataset for testing depth estimation methods in a light field. DLFD contains 39 scenes with disparity range [-4,4] pixels. The light fields are of spatial resolution 512 x 512 and angular resolution 9 x 9. Source: http://clim.inria.fr/Datasets/InriaSynLF/index.html Image Source: http://clim.inria.fr/Datasets/InriaSynLF/index.html

ISOD contains 2,000 manually labelled RGB-D images from 20 diverse sites, each featuring over 30 types of small objects randomly placed amidst the items already present in the scenes. These objects, typically ≤3cm in height, include LEGO blocks, rags, slippers, gloves, shoes, cables, crayons, chalk, glasses, smartphones (and their cases), fake banana peels, fake pet waste, and piles of toilet paper, among others. These items were chosen because they either threaten the safe operation of indoor mobile robots or create messes if run over. In addition to RGB images, ISOD also includes corresponding depth images and IMU readings. A reference image of each floor type was also recorded using a smartphone. This dataset was used as a real-world validation dataset in the original work to explore the performance of the model beyond synthetic data, specifically focusing on the potential application of real-time robot navigation.

This dataset is useful for doing research in the field of mars surface monocular depth estimation. The dataset is composed of 250k patches where each patch is a 3-channels 512 x 512 raster. The first two channels are respectively left and right images of the stereo pair while the third channel is the DTM. Because DTMs are saved with absolute values you have to preprocess in case you want to predict relative values. The Dataset size is 800 GB.

MinNav is a synthetic dataset based on the sandbox game Minecraft. The dataset uses several plug-in program to generate rendered image sequences with time-aligned depth maps, surface normal maps and camera poses. Thanks for the large game's community, there is an extremely large number of 3D open-world environment, users can find suitable scenes for shooting and build data sets through it and they can also build scenes in-game. Source: MineNav: An Expandable Synthetic Dataset Based on Minecraft for Aircraft Visual Navigation

The dataset includes polarimetric, RGB and depth automotive (on the road) data. The data includes synchronized and aligned samples of the following: angle of linear polarization (AoLP) images, degree of linear polarization (DoLP) images, RGB images, lidar scans, ground truth free space segmentation (road segmentation), GNSS / IMU readings (vehicle location, vehicle orientation, vehicle speed, vehicle acceleration, etc.) and calibration matrices. The dataset includes 12,627 samples from 6 different locations. The locations represent typical suburbs where the scenes are not remarkably cluttered, but provide a good distribution of vehicles, pedestrians and buildings. Additionally, the dataset includes free space segmentation of 8,141 images.

The dataset SCARED-C is introduced in the context of assessing robustness in endoscopic depth prediction models. It is part of the EndoDepth benchmark, which is designed to evaluate the performance of monocular depth prediction models specifically for endoscopic scenarios. The dataset features 16 different types of image corruptions, each with five levels of severity, encompassing challenges like lens distortion, resolution alterations, specular reflection, and color changes that are typical in endoscopic imaging. The ground truth is on the original testing set of SCARED. The purpose of SCARED-C is to test the robustness of depth estimation models by exposing them to various common endoscopic corruptions. This dataset is a valuable tool for developing and evaluating depth prediction algorithms that can handle the unique challenges presented by endoscopic procedures, ensuring more accurate and reliable outcomes in medical imaging.

The SimBEV dataset is a collection of 320 scenes spread across all 11 CARLA maps and contains data from a variety of sensors, including five camera types (RGB, semantic segmentation, instance segmentation, depth, and optical flow), lidar, semantic lidar, radar, GNSS, and IMU, along with 3D object bounding boxes and accurate bird's-eye view (BEV) ground truth. With each scene lasting 16 seconds at a frame rate of 20 Hz, the SimBEV dataset contains 102,400 annotated frames, over 8 million 3D object bounding boxes, and more than 2.5 billion BEV ground truth labels.

The dataset contains procedurally generated images of transparent vessels containing liquid and objects . The data for each image includes segmentation maps, 3d depth maps, and normal maps of of the liquid or object inside the transparent vessel, and the vessel. In addition, the properties of the materials inside the containers are given(color/transparency/roughness/metalness). In addition, a natural image benchmark for the 3d/depth estimation of objects inside transparent containers is supplied. 3d models of the objects (GTLF) are also supplied.

A visible-light and thermal-infrared images dataset for dual-spectrum depth estimation.

75k photos of windows + 21k synthetic renders of building windows.

Abstract: We introduce the multi-spectral stereo (MS2) outdoor dataset, including stereo RGB, stereo NIR, stereo thermal, stereo LiDAR data, and GPS/IMU information. Our dataset provides rectified and synchronized 184K data pairs taken from city, residential, road, campus, and suburban areas in the morning, daytime, and nighttime under clear-sky, cloudy, and rainy conditions. We designed the dataset to explore various computer vision algorithms from multi-spectral sensor data to achieve high-level performance, reliability, and robustness against challenging environments. MS2 dataset provides: * 1. (Synchronized) Stereo RGB images / Stereo NIR images / Stereo thermal images * 2. (Synchronized) Stereo LiDAR scans / GPS/IMU navigation data * 3. Projected depth map (in RGB, NIR, thermal image planes) * 4. Odometry data (in RGB, NIR, thermal cameras, and LiDAR coordinates)

We propose a new light field image database called “PINet” inheriting the hierarchical structure from WordNet. It consists of 7549 LIs captured by Lytro Illum, which is much larger than the existing databases. The images are manually annotated to 178 categories according to WordNet, such as cat, camel, bottle, fans, etc. The registered depth maps are also provided. Each image is generated by processing the raw LI from the camera by Light Field Toolbox v0.4 for demosaicing and devignetting. PINet is the largest light field image dataset. More details can be found in https://github.com/VincentChandelier/SADN