Dense Wide-Baseline Scene Flow From Two Handheld Video Cameras

Christian Richardt1,2,3   Hyeongwoo Kim1   Levi Valgaerts1   Christian Theobalt1
1Max Planck Institute for Informatics   2Intel Visual Computing Institute   3University of Bath


We propose a new technique for computing dense scene flow from two handheld videos with wide camera baselines and different photometric properties due to different sensors or camera settings like exposure and white balance. Our technique innovates in two ways over existing methods: (1) it supports independently moving cameras, and (2) it computes dense scene flow for wide-baseline scenarios. We achieve this by combining state-of-the-art wide-baseline correspondence finding with a variational scene flow formulation. First, we compute dense, wide-baseline correspondences using DAISY descriptors for matching between cameras and over time. We then detect and replace occluded pixels in the correspondence fields using a novel edge-preserving Laplacian correspondence completion technique. We finally refine the computed correspondence fields in a variational scene flow formulation. We show dense scene flow results computed from challenging datasets with independently moving, handheld cameras of varying camera settings.


  • Paper (PDF)

  • Supplementary Document (PDF)

  • Supplementary Video (PDF)


We thank the authors of the used datasets. Funded by ERC Starting Grant 335545 CapReal