Lee-Kang (Lester) Liu - Publications - GlobalSIP2015 Supplementary Materials

Spatio-Temporal Depth Reconstruction from A subset of Samples.


High-quality depth data is needed in many advanced computer vision as well as 3D and virtual reality applications. To surpass the hardware limitations, computational approaches are commonly exploited, and the solutions are from the intersection of two fundamental problems, depth map super-resolution and inpainting, leading to a general problem of reconstructing depth data from a subset of samples.Extending our previous work [1], we in this paper propose a spatio-temporal depth reconstruction algorithm, which is scalable to temporal volume. We also present an updated parameter tuning approach and a speed-up scheme for depth video reconstruction application. Experimental results show that the proposed STDR algorithm outperforms the existing methods and is robust to varying temporal volumes.

This supplymentary material mainly contains additional experimental results for the depth video reconstruction (Using dataset from [2]). Statistical analysis of these results are shown in Table I of this paper. We conduct the depth video reconstruction under our depth video configurations (Speed-up scheme + updated parameters + STDR Algorithm).

  • Video data: Tanks [*.avi], Books [*.avi], Temples [*.avi].
  • Snapshots on reconstructed depth video sequences:
  • Smiley faceSmiley faceSmiley face
  • Evaluations:
  • Smiley face
  • (additional) Consistency:
  • Smiley faceSmiley faceSmiley face

    [1] L.-K, Liu, S.H. Chan, and T.Q. Nguyen, "Depth reconstruction from sparse samples: Representation, algorithm, and sampling," IEEE Trans. on Image Process., vol. 24, no. 6, pp. 1983-1996, Jun. 2015.

    [2] C. Richardt, D. Orr, I. Davies, A. Criminisi, and N.A. Dodgson "Real-time spatio-temporal stereo matching using the dual-cross-bilateral grid," in Proceeding of the Euro. Conf. on Computer Vision (ECCV'10), Sep. 2010, vol. 6313, pp. 510-523.

    [3] S. Hawe, M. Lleinsteuber, and K. Diepold, "Dense disparity maps from sparse disparity measurements," in Proceeding IEEE Intelational Conf. on Computer Vision (ICCV'11), Nov. 2011, pp. 2126-2133.