Virtual KITTI 2

By Yohann Cabon, Naila Murray, Martin Humenberger. arXiv.org, 2020

481 citations recorded by the source corpus.

This paper introduces an updated version of the well-known Virtual KITTI dataset which consists of 5 sequence clones from the KITTI tracking benchmark. In addition, the dataset provides different variants of these sequences such as modified weather conditions (e.g. fog, rain) or modified camera configurations (e.g. rotated by 15 degrees). For each sequence, we provide multiple sets of images containing RGB, depth, class segmentation, instance segmentation, flow, and scene flow data. Camera parameters and poses as well as vehicle locations are available as well. In order to showcase some of the dataset's capabilities, we ran multiple relevant experiments using state-of-the-art algorithms from the field of autonomous driving. The dataset is available for download at this https URL.

Subfields: Artificial Intelligence, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/c6e57b2d36a4231cef82d7e0e27413ae4bb4dee5

How researchers see this paper

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

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

GMFlow: Learning Optical Flow via Global Matching (2021, methodology): “Our framework still has room for future improvement in occluded regions, as can be seen from the KITTI results in Table 6.”
Grounding Image Matching in 3D with MASt3R (2024, methodology): “We train our network with a mixture of 14 datasets: Habitat [74], ARKitScenes [20], Blended MVS [112], MegaDepth [48], Static Scenes 3D [57], ScanNet++ [113], CO3D-v2 [67], Waymo [83], Map-free [5], WildRgb [2], VirtualKitti [12], Unreal4K [91], TartanAir [103] and an internal dataset.”
SAM 2: Segment Anything in Images and Videos (2024, background): “…Camera Traps (LCT) (Haucke & Steinhage, 2021), VOST (Tokmakov et al., 2022), LV-VIS (Wang et al., 2023), FBMS (Brox et al., 2010), Virtual KITTI 2 (Cabon et al., 2020), Corsican Fire Database (CFD) (Toulouse et al., 2017), VIPSeg (Miao et al., 2022), Drosophila Heart OCM (DH OCM) (Fishman et al.,…”
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation (2023, unknown): “The second dataset, Virtual KITTI [7] is a synthetic street-scene dataset featuring 5 scenes under varying conditions like weather or camera perspectives.”
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D (2021, background): “There also exist several synthetic urban datasets [17], [32], [82], [86].”
Depth Anything V2 (2024, unknown): “Such distribution shift makes models struggle to transfer from synthetic to real images, even if the two data sources share similar layouts [57, 9].”
Unifying Flow, Stereo and Depth Estimation (2022, methodology): “Then, we finetune on the mixed Virtual KITTI 2 [100] and DrivingStereo [113] datasets.”
VGGT: Visual Geometry Grounded Transformer (2025, unknown): “Hence, while the feed-forward mode of VGGT outperforms all previous alternatives (whether they are feed-forward or not), there is still room for improvement since post-optimization still brings beneﬁts.”
Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning (2020, methodology): “Since Virtual KITTI 2 [3] does not provide any default train/validation/test split, for each scene/condition we use the ﬁrst 70% of the sequence for training, the next 15% for validation and the ﬁnal 15% for test.”
Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation (2024, unknown): “12, including comic-style (Row 2) and CG(computer graphics)-generated objects (Row5)”
Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation (2022, methodology): “Results of experiments on several KITTI scenes demonstrate state-ofthe-art performance for novel view synthesis and panoptic segmentation for challenging outdoor scenes with multiple dynamic objects.”