Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments

Homeyer, Christian; Lange, O.; Schnörr, Christoph

doi:10.1007/978-3-031-09037-0_31

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, lots of efforts have been made to extract the multi-view geometry from a monocular RGB video [18,50,51,54] or for self-supervised depth estimation [42]. However, epipolar constraint does not hold in dynamic environments, and dynamic objects need to be filtered out in the estimation pipeline [22], which limits their applications. On the other hand, how to efficiently utilize the temporal correlation is less explored.…”

Section: Depth Video Processingmentioning

confidence: 99%

Consistent Direct Time-of-Flight Video Depth Super-Resolution

Sun¹,

Ye²,

Xiong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Figure 1. We propose the first multi-frame approaches, dToF depth video super-resolution (DVSR) and histogram video super-resolution (HVSR), to super-resolve low-resolution dToF sensor videos with the high-resolution RGB frame guidance. The point cloud visualizations of depth predictions reveal that, by utilizing multi-frame correlation, DVSR predicts significantly better geometry compared to state-of-theart per-frame depth enhancement networks [41] while being more lightweight; HVSR further improves the fidelity of geometry and reduces flying pixels by utilizing the dToF histogram information. Besides the improvements in per-frame estimation, we highly recommend readers to check out the supplementary video, which visualizes the significant improvements in temporal stability across the entire sequences.

show abstract