TY - GEN
T1 - Monocular Depth by NonLinear Diffusion
AU - Dimiccol, Mariella
AU - Morel, Jean-Michel
AU - Salembier, Philippe
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2008
Y1 - 2008
N2 - Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth relationships of depicted objects. According to Kanizsa, mechanisms called amodal and modal completion permit to transform these local relative depth cues into a global depth reconstruction. In this paper, we propose a mathematical and computational translation of gestalt depth perception theory, from the detection of local depth cues to their synthesis into a consistent global depth perception. The detection of local depth cues is built on the response of a line segment detector (LSD), which works in a linear time relative to the image size without any parameter tuning. The depth synthesis process is based on the use of a nonlinear iterative filter which is asymptotically equivalent to the Perona-Malik partial differential equation (PDE). Experimental results are shown on several real images and demonstrate that this simple approach can account a variety of phenomena such as visual completion, transparency and self-occlusion.©2008 IEEE.
AB - Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth relationships of depicted objects. According to Kanizsa, mechanisms called amodal and modal completion permit to transform these local relative depth cues into a global depth reconstruction. In this paper, we propose a mathematical and computational translation of gestalt depth perception theory, from the detection of local depth cues to their synthesis into a consistent global depth perception. The detection of local depth cues is built on the response of a line segment detector (LSD), which works in a linear time relative to the image size without any parameter tuning. The depth synthesis process is based on the use of a nonlinear iterative filter which is asymptotically equivalent to the Perona-Malik partial differential equation (PDE). Experimental results are shown on several real images and demonstrate that this simple approach can account a variety of phenomena such as visual completion, transparency and self-occlusion.©2008 IEEE.
UR - https://www.scopus.com/pages/publications/65249110916
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-65249110916&origin=recordpage
U2 - 10.1109/ICVGIP.2008.97
DO - 10.1109/ICVGIP.2008.97
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9780769534763
T3 - Proceedings - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008
SP - 95
EP - 102
BT - Proceedings - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008
T2 - 6th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2008
Y2 - 16 December 2008 through 19 December 2008
ER -