3 papers
cs.CV2020
Learning to Correct 3D Reconstructions from Multiple Views
Ştefan Săftescu, Paul Newman
This paper is about reducing the cost of building good large-scale 3D reconstructions post-hoc. We render 2D views of an existing reconstruction and train a convolutional neural ne…
cs.CV2019
Learning Geometrically Consistent Mesh Corrections
Ştefan Săftescu, Paul Newman
Building good 3D maps is a challenging and expensive task, which requires high-quality sensors and careful, time-consuming scanning. We seek to reduce the cost of building good rec…
cs.CV2018
Meshed Up: Learnt Error Correction in 3D Reconstructions
Michael Tanner, Stefan Saftescu, Alex Bewley +1
Dense reconstructions often contain errors that prior work has so far minimised using high quality sensors and regularising the output. Nevertheless, errors still persist. This pap…