DENSER Cities: A System for Dense Efficient Reconstructions of Cities

by   Michael Tanner, et al.

This paper is about the efficient generation of dense, colored models of city-scale environments from range data and in particular, stereo cameras. Better maps make for better understanding; better understanding leads to better robots, but this comes at a cost. The computational and memory requirements of large dense models can be prohibitive. We provide the theory and the system needed to create city-scale dense reconstructions. To do so, we apply a regularizer over a compressed 3D data structure while dealing with the complex boundary conditions this induces during the data-fusion stage. We show that only with these considerations can we swiftly create neat, large, "well behaved" reconstructions. We evaluate our system using the KITTI dataset and provide statistics for the metric errors in all surfaces created compared to those measured with 3D laser. Our regularizer reduces the median error by 40 in 3.4 km of dense reconstructions with a median accuracy of 6 cm. For subjective analysis, we provide a qualitative review of 6.1 km of our dense reconstructions in an attached video. These are the largest dense reconstructions from a single passive camera we are aware of in the literature.


page 1

page 4

page 7

page 8


DeepFusion: Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions

While the keypoint-based maps created by sparse monocular simultaneous l...

Combining SLAM with muti-spectral photometric stereo for real-time dense 3D reconstruction

Obtaining dense 3D reconstrution with low computational cost is one of t...

Meshed Up: Learnt Error Correction in 3D Reconstructions

Dense reconstructions often contain errors that prior work has so far mi...

StereoDRNet: Dilated Residual Stereo Net

We propose a system that uses a convolution neural network (CNN) to esti...

Dense Voxel 3D Reconstruction Using a Monocular Event Camera

Event cameras are sensors inspired by biological systems that specialize...

Understanding Context to Capture when Reconstructing Meaningful Spaces for Remote Instruction and Connecting in XR

Recent technological advances are enabling HCI researchers to explore in...

Deep Multi-View Stereo gone wild

Deep multi-view stereo (deep MVS) methods have been developed and extens...

Please sign up or login with your details

Forgot password? Click here to reset