Automatic dense visual semantic mapping from street-level imagery

107 citations recorded by the source corpus.

How researchers see this paper

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

Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction (2015, background): “1, is a crucial prerequisite for a variety of applications, including robot navigation [1], [2], semantic mapping [3], [4], wearable and/or assistive technology [5], [6], and change detection [7].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Sengupta et al. (2012) present an approach to generate a semantic overhead map of an urban scene from street level images.”
Learning Where to Classify in Multi-view Semantic Segmentation (2014, methodology): “[4] classified 2D images and then aggregated their labels to provide an overhead map of the scene.”
Cross-view Transformers for real-time Map-view Semantic Segmentation (2022, methodology): “One common technique is to assume the scene is mostly planar and represent the image to map-view transformation as a simple homography [2, 9, 16, 22, 36, 49].”
Semantic mapping for mobile robotics tasks: A survey (2015, methodology): “Similarly, in [69] the generation of semantic labels for the street images by directly segmenting the frames is reported.”