2017 · 46 citations · 53 references
ComputingComputer ScienceComputer VisionRobot VisionVisual PerceptionObject DetectionObject RecognitionOptical FlowScene ReconstructionScene UnderstandingVisual Odometry3D Object Detection3D Scene Modeling3D Scene UnderstandingBenchmark DatasetsGround Truth Data CollectionGround-truth ValidationSemantic Scene UnderstandingSimulated Environments
We present a benchmark suite for visual perception. The benchmark comprises over 250 K high‑resolution video frames annotated for low‑ and high‑level vision tasks, collected while traversing 184 km of diverse virtual environments, and was built using a novel method that extracts ground‑truth data from simulated worlds without requiring source‑code access. Ground‑truth annotations are available for every frame, the scene composition closely mirrors real environments, perceptual tests confirm realism, and baseline analyses of state‑of‑the‑art methods reveal performance gaps and future research challenges.
We present a benchmark suite for visual perception. The benchmark is based on more than 250K high-resolution video frames, all annotated with ground-truth data for both low-level and high-level vision tasks, including optical flow, semantic instance segmentation, object detection and tracking, object-level 3D scene layout, and visual odometry. Ground-truth data for all tasks is available for every frame. The data was collected while driving, riding, and walking a total of 184 kilometers in diverse ambient conditions in a realistic virtual world. To create the benchmark, we have developed a new approach to collecting ground-truth data from simulated worlds without access to their source code or content. We conduct statistical analyses that show that the composition of the scenes in the benchmark closely matches the composition of corresponding physical environments. The realism of the collected data is further validated via perceptual experiments. We analyze the performance of state-of-the-art methods for multiple tasks, providing reference baselines and highlighting challenges for future research.
53
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky, Jia Deng, Hao Su et al. · International Journal of Computer Vision · 2015 · 40.2K citations
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun · 2012 · 14.4K citations
The Cityscapes Dataset for Semantic Urban Scene Understanding
Marius Cordts, Mohamed Omran, Sebastian Ramos et al. · 2016 · 11.9K citations