Gaussian blur approximation suitable for GPU

Details Gaussian blur approximation suitable for GPU Gaussian blur approximation suitable for GPU

2004-06-24

2008-07-08

Bella, Matthew C (Department: 2624)

Image analysis

Image enhancement or restoration

Image filter

C382S265000, C348S597000

Reexamination Certificate

active

07397964

ABSTRACT:
A Gaussian blur approximation is applied to an image by repeated down-sampling operations followed by an up-sample operation. By using a truncated Gaussian filter as the down-sample filter, the frequency spectrum removed during down-sampling operations closely approximates the frequency spectrum lost during a true Gaussian blur operation. While any “good” up-sample filter may be used, up-sampling via linear interpolation may be especially beneficial in systems having a dedicated graphics processing unit. One benefit of the described technique is that it is computationally less costly to implement than a Gaussian blur. Another benefit is that this computational benefit increases as the size of the blur increases—becoming significant even for small blurs. Yet another benefit of the invention is that a judicious selection of pixel address to convolve with the filter leads to substantially reduced number of texture lookups required to effect a convolution.

REFERENCES:
patent: 5148497 (1992-09-01), Pentland et al.
patent: 5388201 (1995-02-01), Hourvitz et al.
patent: 5436672 (1995-07-01), Medioni et al.
patent: 5467404 (1995-11-01), Vuylsteke et al.
patent: 5490246 (1996-02-01), Brotsky et al.
patent: 5694447 (1997-12-01), Ito
patent: 5793376 (1998-08-01), Tanaka et al.
patent: 5832055 (1998-11-01), Dewaele
patent: 5933148 (1999-08-01), Oka et al.
patent: 5949409 (1999-09-01), Tanaka et al.
patent: 6006231 (1999-12-01), Popa
patent: 6031937 (2000-02-01), Graffagnino
patent: 6075543 (2000-06-01), Akeley
patent: 6166748 (2000-12-01), Van Hook et al.
patent: 6211890 (2001-04-01), Ohba
patent: 6246418 (2001-06-01), Oka
patent: 6249315 (2001-06-01), Holm
patent: 6272558 (2001-08-01), Hui et al.
patent: 6356652 (2002-03-01), Vuylsteke
patent: 6369823 (2002-04-01), Ohba
patent: 6369830 (2002-04-01), Brunner et al.
patent: 6411301 (2002-06-01), Parikh et al.
patent: 6421058 (2002-07-01), Parikh et al.
patent: 6424348 (2002-07-01), Parikh
patent: 6426755 (2002-07-01), Deering
patent: 6452600 (2002-09-01), Parikh et al.
patent: 6456290 (2002-09-01), Parikh et al.
patent: 6466218 (2002-10-01), Parikh et al.
patent: 6489963 (2002-12-01), Parikh et al.
patent: 6526174 (2003-02-01), Graffagnino
patent: 6571328 (2003-05-01), Liao et al.
patent: 6577317 (2003-06-01), Duluk, Jr. et al.
patent: 6580430 (2003-06-01), Hollis et al.
patent: 6609977 (2003-08-01), Shimizu et al.
patent: 6614444 (2003-09-01), Duluk, Jr. et al.
patent: 6618048 (2003-09-01), Leather
patent: 6636214 (2003-10-01), Leather et al.
patent: 6639595 (2003-10-01), Drebin et al.
patent: 6664958 (2003-12-01), Leather et al.
patent: 6664962 (2003-12-01), Komsthoeft et al.
patent: 6697074 (2004-02-01), Parikh et al.
patent: 6707462 (2004-03-01), Peercy et al.
patent: 6717599 (2004-04-01), Olano
patent: 6792575 (2004-09-01), Samaniego et al.
patent: 6999634 (2006-02-01), Hong
patent: 7065255 (2006-06-01), Chen et al.
patent: 7068851 (2006-06-01), Berkner
patent: 7177481 (2007-02-01), Kaji
patent: 7245400 (2007-07-01), Schuppan
patent: 2001/0013895 (2001-08-01), Aizawa et al.
patent: 2002/0093516 (2002-07-01), Brunner et al.
patent: 2002/0118217 (2002-08-01), Fujiki
patent: 2002/0118875 (2002-08-01), Wilensky
patent: 2002/0159648 (2002-10-01), Alderson et al.
patent: 2002/0174181 (2002-11-01), Wei
patent: 2002/0176113 (2002-11-01), Edgar
patent: 2003/0123739 (2003-07-01), Graffagnino
patent: 2003/0174136 (2003-09-01), Emberling et al.
patent: 2003/0223622 (2003-12-01), Simon et al.
patent: 2005/0232507 (2005-10-01), Zimmer
patent: 2007/0183683 (2007-08-01), Ricard et al.
patent: 548 586 (1993-06-01), None
patent: 0 694 879 (1996-01-01), None
patent: 1 383 080 (2004-01-01), None
patent: 0 972 273 (2004-03-01), None
patent: WO 98/45815 (1998-10-01), None
patent: WO 02/09039 (2002-01-01), None
patent: WO 2004-027707 (2004-04-01), None
nVIDIA, “Cg—Teaching Cg” Power Point Presentation, Author and date unknown.
Shantzis, “A Model for Efficient and Flexible Image Computing” Computer Graphics Proceedings, Annual Conference Series, 1994, pp. 147-154.
Akeley, et al., “Real-Time Graphics Architecture” http://www.graphics.stanford.edu/courses/cs448a-01-fall, The OpenGL® Graphics System—CS448 Lecture 15, Fall 2001, pp. 1-20.
Gelder, et al., “Direct Volume Rendering with Shading via Three-Dimensional Textures” Computer Science Dept., Univ. of California, Santa Cruz, CA 95064.
Elliott, “Programming Graphics Processors Functionally,”.
Segal, et al., “The OpenGL® Graphics System: A Specification (Version 1.5)” Copyright © 1992-2003 Silicon Graphics, Inc., Oct. 30, 2003.
International Search report dated Jul. 27, 2005 (PCT/US 05/008804; 119-0033WO).
International Search report dated Aug. 8, 2005 (PCT/US 05/008805; 119-0034WO).
Haeberli, P. et al., “The Accumulation Buffer: Hardware Support for High-Quality Rendering,” Computer Graphics, New York, NY, vol. 24, No. 4, Aug. 1, 1990, pp. 309-318.

Affiliated with

Also associated with

Rating

Gaussian blur approximation suitable for GPU does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Gaussian blur approximation suitable for GPU, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Gaussian blur approximation suitable for GPU will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3964367