Towards Urban 3D Reconstruction from Video

Abstract

The paper introduces a data collection system and a processing pipeline for automatic geo-registered 3D reconstruction of urban scenes from video. The system collects multiple video streams, as well as GPS and INS measurements in order to place the reconstructed models in georegistered coordinates. Besides high quality in terms of both geometry and appearance, we aim at real-time performance. Even though our processing pipeline is currently far from being real-time, we select techniques and we design processing modules that can achieve fast performance on multiple CPUs and GPUs aiming at real-time performance in the near future. We present the main considerations in designing the system and the steps of the processing pipeline. We show results on real video sequences captured by our system.

LSD-SLAM: Large-Scale Direct Monocular SLAM

“…Yet, since the estimation of the high-dimensional feature space is tedious, they are rarely used in practice. To obtain dense reconstructions, the estimated camera poses can be used to subsequently reconstruct dense maps, using multiview stereo [2]. Direct Methods.…”

Is There a Procedural Logic to Architecture?

“…Façade modelling in form of image-based architectural modelling [1,28] and semantic segmentation [3] is not relevant to our problem due to its restrictions to pure visualization and reporting. In fact, the work performed in imagebase city modelling is a pre-processing step to our pipeline.…”

Modeling the World from Internet Photo Collections

“…Notable examples include the semi-automatic Façade system (Debevec et al 1996), which was used to reconstruct compelling flythroughs of the University of California Berkeley campus; automatic architecture reconstruction systems such as that of Dick et al (2004); and the MIT City Scanning Project (Teller et al 2003), which captured thousands of calibrated images from an instrumented rig to construct a 3D model of the MIT campus. There are also several ongoing academicStanford CityBlock Project (Román et al 2004), which uses video of city blocks to create multi-perspective strip images; and the UrbanScape project of Akbarzadeh et al (2006). Our work differs from these previous approaches in that we only reconstruct a sparse 3D model of the world, since our emphasis is more on creating smooth 3D transitions between photographs rather than interactively visualizing a 3D world.…”