Vision meets robotics: The KITTI dataset

By Andreas Geiger, Philip Lenz, Christoph Stiller, Raquel Urtasun. 2013

10,594 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

ImageNet Large Scale Visual Recognition Challenge (2014, background): “…the aforementioned PASCAL VOC (Everingham et al., 2012), Labeled Faces in the Wild (Huang et al., 2007) for unconstrained face recognition, Reconstruction meets Recognition (Urtasun et al., 2014) for 3D reconstruction and KITTI (Geiger et al., 2013) for computer vision in autonomous driving.”
On Robustness and Transferability of Convolutional Neural Networks (2020, background): “The structured group contains the following tasks: counting and distance prediction on CLEVR [33], pixel-location and orientation prediction on dSprites [45], camera elevation and object orientation on SmallNORB [41], object distance on DMLab [4] and vehicle distance on KITTI [19].”
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, background): “KITTI-Dist (Geiger et al., 2013) The KITTI task consists in predicting the (binned) depth to the vehicle (car, van, or truck) in the image.”
Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “Subsequently, it has been applied to multiple tasks like feature point detection [18, 11, 19], face detection [27] and object detection [3, 7, 9].”
The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, background): “Out of the previously discussed datasets, only Cityscapes and KITTI provide instance-level annotations for humans and vehicles.”
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, background): “Visual recognition has become ubiquitous in our society [60], with applications in geolocalization [51], action recognition [57], street number transcription [44], satellite remote sensing [22], medical imaging [62], self-driving cars [19], etc.”
Visual Prompt Tuning (2022, neutral): “800/1000 200 15,000 Clevr/distance [34] 6 15,000 DMLab [3] 6 22,735 KITTI/distance [20] 4 711 dSprites/location [53] 16 73,728 dSprites/orientation [53] 16 73,728 SmallNORB/azimuth [40] 18 12,150 SmallNORB/elevation [40] 9 12,150”
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding (2020, neutral): “This distribution is roughly consistent with existing indoor depth datasets [68, 74, 82], but is noticeably different from out-door datasets [17, 25].”
WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving (2019, background): “Task/Info Quantity KITTI [17] Cityscapes [10] Mapillary [39] nuScenes [6] ApolloScape [24] BDD100k [59] WoodScape Ours”
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (2021, methodology): “For transfer learning evaluation we use 4 popular computer vision datasets from the VTAB benchmark [40]: CIFAR-100 [20], Oxford IIIT Pets [24] (or Pets37 for short), Resisc45 [5] and Kittidistance [11].”
Multi-Scale Context Aggregation by Dilated Convolutions (2015, methodology): “Fine-tuning was performed for 50K iterations with a learning rate of 10 − 5 .”
Learning to See by Moving (2015, methodology): “In order to test our hypothesis, we trained multilayer neural networks to predict the camera transformation be-tween pairs of images.”
Dense-Captioning Events in Videos (2017, background): “er events, MSRVTT [55], MSVD [6] and YouCook [7] collected a dataset with slightly longer length, at the cost of a few descriptions than previous datasets. To further improve video annotations, KITTI [12] and TACoS [36] also temporally localized their video descriptions. Orthogonally, in an effort t”
Learning Image Representations Tied to Ego-Motion (2015, background): “(2) KITTI [6, 7]: This dataset contains videos with registered GPS/IMU sensor streams captured on a car driving around 4 types of areas (location classes): “campus”, “city”, “residential”, “road”.”
Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, methodology): “While we train and test our method on the ShapeNet dataset, we also present qualitative results for the KITTI [22] and the Online Products dataset [49].”
Learning To Simulate (2018, methodology): “Since the semantic label space of KITTI and our CARLA simulator are not identical, we again focus on segmentation of cars by measuring IoU for that category.”
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (2023, background): “[12] Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun.”
Expert Gate: Lifelong Learning with a Network of Experts (2016, methodology): “We show experiments conducted on three domains/tasks: for Highway, we use the data from DFN [7], with the same train/test split; for Residential data, we use the two longest sequences from the KITTI dataset [10]; and for City data, we use the Stuttgart sequence from the CityScapes dataset”