JJMC89 bot (talk | contribs) m Add {{drafts moved from mainspace}} |
Citation bot (talk | contribs) Altered template type. Add: pages, issue, volume, date, doi, journal, title, authors 1-6. Removed parameters. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Jay8g | Category:CS1 errors: empty unknown parameters | #UCB_Category 1/9 |
||
Line 4: | Line 4: | ||
He works on both computer graphics and vision, spanning topics such as [[computational photography]], differentiable rendering, compilers for high-performance imaging, and video magnification. |
He works on both computer graphics and vision, spanning topics such as [[computational photography]], differentiable rendering, compilers for high-performance imaging, and video magnification. |
||
Several of his projects focus on trying to reveal visual signals that are otherwise imperceptible to the human eye. With MIT colleagues he developed a “motion microphone” device that can take silent video of an object and magnify the minute visual vibrations to recreate the sounds present in the room<ref>{{cite web|url=https://people.csail.mit.edu/mrub/VisualMic/#seeing_sound|website=mit.edu}}</ref>. He also helped develop a system that can look at short video clips of people sitting still and visual magnify their movement and skin-color changes such that he could measure people’s heart-rates<ref>{{cite |
Several of his projects focus on trying to reveal visual signals that are otherwise imperceptible to the human eye. With MIT colleagues he developed a “motion microphone” device that can take silent video of an object and magnify the minute visual vibrations to recreate the sounds present in the room<ref>{{cite web|url=https://people.csail.mit.edu/mrub/VisualMic/#seeing_sound|website=mit.edu |title=The Visual Microphone }}</ref>. He also helped develop a system that can look at short video clips of people sitting still and visual magnify their movement and skin-color changes such that he could measure people’s heart-rates<ref>{{cite journal|url=https://dl.acm.org/doi/abs/10.1145/2185520.2185561|journal=ACM Transactions on Graphics|doi=10.1145/2185520.2185561 |title=Eulerian video magnification for revealing subtle changes in the world |date=2012 |last1=Wu |first1=Hao-Yu |last2=Rubinstein |first2=Michael |last3=Shih |first3=Eugene |last4=Guttag |first4=John |last5=Durand |first5=Frédo |last6=Freeman |first6=William |volume=31 |issue=4 |pages=1–8 }}</ref>, enabling new applications for remote health monitoring. |
||
Another project uses video of shadows on the floor to be able to detect things hidden around the corner<ref>{{cite web|url=https://www.csail.mit.edu/news/algorithm-your-blind-spot|website=mit.edu}}</ref>, an insight that could help self-driving cars be able to observe objects in their blind spots. His team’s “Interactive Dynamic Video”<ref>{{cite web|url=https://news.mit.edu/2016/touching-objects-in-videos-with-interactive-dynamic-video-0802|website=mit.edu}}</ref> system lets them test how an object would respond to different kinds of touch based only on a short video clip of it. |
Another project uses video of shadows on the floor to be able to detect things hidden around the corner<ref>{{cite web|url=https://www.csail.mit.edu/news/algorithm-your-blind-spot|website=mit.edu |title=An algorithm for your blind spot | MIT CSAIL }}</ref>, an insight that could help self-driving cars be able to observe objects in their blind spots. His team’s “Interactive Dynamic Video”<ref>{{cite web|url=https://news.mit.edu/2016/touching-objects-in-videos-with-interactive-dynamic-video-0802|website=mit.edu |title=Reach in and touch objects in videos with "Interactive Dynamic Video" |date=2 August 2016 }}</ref> system lets them test how an object would respond to different kinds of touch based only on a short video clip of it. |
||
He has also created several influential tools for computer graphics. With Saman Amarasinghe and Jonathan Ragan-Kelley he invented a domain-specific language (DSL) called Halide<ref>{{cite web|url=https://halide-lang.org}}</ref>, to be used for image processing. Their research showed that Halide offers major speed and performance gains<ref>{{cite web|url=https://news.mit.edu/2012/better-programming-language-for-image-processing-0802|website=mit.edu}}</ref> over hand-engineered code, and uses code that is also much easier to read. Halide has received interest from both academic and industry partners, who have incorporated it into products such as the Google Pixel’s cameras<ref>{{cite web|url=https://betterprogramming.pub/write-fast-and-maintainable-code-with-halide-part-1-6a5c3a519250}}</ref>, Adobe’s Photoshop filters and YouTube’s video-uploading system. |
He has also created several influential tools for computer graphics. With Saman Amarasinghe and Jonathan Ragan-Kelley he invented a domain-specific language (DSL) called Halide<ref>{{cite web|url=https://halide-lang.org}}</ref>, to be used for image processing. Their research showed that Halide offers major speed and performance gains<ref>{{cite web|url=https://news.mit.edu/2012/better-programming-language-for-image-processing-0802|website=mit.edu |title=Writing graphics software gets much easier |date=2 August 2012 }}</ref> over hand-engineered code, and uses code that is also much easier to read. Halide has received interest from both academic and industry partners, who have incorporated it into products such as the Google Pixel’s cameras<ref>{{cite web|url=https://betterprogramming.pub/write-fast-and-maintainable-code-with-halide-part-1-6a5c3a519250 |title=Writing Fast and Maintainable Code with Halide —The Pilot Episode |date=24 April 2022 }}</ref>, Adobe’s Photoshop filters and YouTube’s video-uploading system. |
||
Durand received his PhD from Grenoble University, France, in 1999, supervised by Claude Puech and George Drettakis. From 1999 to 2002 he was a postdoc in MIT’s Computer Graphics Group. |
Durand received his PhD from Grenoble University, France, in 1999, supervised by Claude Puech and George Drettakis. From 1999 to 2002 he was a postdoc in MIT’s Computer Graphics Group. |
||
He co-organized the first Symposium on Computational Photography and Video<ref>{{cite web|url=http://people.csail.mit.edu/fredo/scpv/index.htm|website=mit.edu}}</ref> in 2005, and the first International Conference on Computational Photography<ref>{{cite web|url=http://groups.csail.mit.edu/graphics/iccp09/|website=mit.edu}}</ref> in 2009. |
He co-organized the first Symposium on Computational Photography and Video<ref>{{cite web|url=http://people.csail.mit.edu/fredo/scpv/index.htm|website=mit.edu |title=Symposium on Computational Photography and Video }}</ref> in 2005, and the first International Conference on Computational Photography<ref>{{cite web|url=http://groups.csail.mit.edu/graphics/iccp09/|website=mit.edu |title=ICCP 2009 News }}</ref> in 2009. |
||
Durand received an inaugural Eurographics Young Researcher Award<ref>{{cite web|url=http://www.mpi-sb.mpg.de/~liegl/eg-awards/website/eg-awards_main.html |
Durand received an inaugural Eurographics Young Researcher Award<ref>{{cite web|url=http://www.mpi-sb.mpg.de/~liegl/eg-awards/website/eg-awards_main.html}}</ref> in 2004, an NSF CAREER award<ref>{{cite web|url=https://www.nsf.gov/awardsearch/showAward?AWD_ID=0447561|website=nsf.gov |title=NSF Award Search: Award # 0447561 - CAREER: Transient Signal Processing for Realistic Imagery }}</ref> in 2005, an inaugural Microsoft Research New Faculty Fellowship<ref>{{cite web|url=http://research.microsoft.com/ur/us/nff/2005fellows.aspx|website=microsoft.com |title=Microsoft Research – Emerging Technology, Computer, and Software Research }}</ref> in 2005, a Sloan fellowship<ref>{{cite web|url=http://www.sloan.org/programs/fellowshiplist.shtml|website=sloan.org}}</ref> in 2006, a Spira award for distinguished teaching in 2007, and the ACM SIGGRAPH Computer Graphics Achievement Award<ref>{{cite web|url=http://s2016.siggraph.org/content/acm-siggraph-awards|website=siggraph.org}}</ref> in 2016. |
||
{{Drafts moved from mainspace |date=April 2024}} |
{{Drafts moved from mainspace |date=April 2024}} |
Revision as of 02:31, 24 April 2024
Fredo Durand is a computer scientist at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory (CSAIL), where he helps lead CSAIL’s Computer Graphics Group.
He works on both computer graphics and vision, spanning topics such as computational photography, differentiable rendering, compilers for high-performance imaging, and video magnification.
Several of his projects focus on trying to reveal visual signals that are otherwise imperceptible to the human eye. With MIT colleagues he developed a “motion microphone” device that can take silent video of an object and magnify the minute visual vibrations to recreate the sounds present in the room[1]. He also helped develop a system that can look at short video clips of people sitting still and visual magnify their movement and skin-color changes such that he could measure people’s heart-rates[2], enabling new applications for remote health monitoring.
Another project uses video of shadows on the floor to be able to detect things hidden around the corner[3], an insight that could help self-driving cars be able to observe objects in their blind spots. His team’s “Interactive Dynamic Video”[4] system lets them test how an object would respond to different kinds of touch based only on a short video clip of it.
He has also created several influential tools for computer graphics. With Saman Amarasinghe and Jonathan Ragan-Kelley he invented a domain-specific language (DSL) called Halide[5], to be used for image processing. Their research showed that Halide offers major speed and performance gains[6] over hand-engineered code, and uses code that is also much easier to read. Halide has received interest from both academic and industry partners, who have incorporated it into products such as the Google Pixel’s cameras[7], Adobe’s Photoshop filters and YouTube’s video-uploading system.
Durand received his PhD from Grenoble University, France, in 1999, supervised by Claude Puech and George Drettakis. From 1999 to 2002 he was a postdoc in MIT’s Computer Graphics Group.
He co-organized the first Symposium on Computational Photography and Video[8] in 2005, and the first International Conference on Computational Photography[9] in 2009.
Durand received an inaugural Eurographics Young Researcher Award[10] in 2004, an NSF CAREER award[11] in 2005, an inaugural Microsoft Research New Faculty Fellowship[12] in 2005, a Sloan fellowship[13] in 2006, a Spira award for distinguished teaching in 2007, and the ACM SIGGRAPH Computer Graphics Achievement Award[14] in 2016.
- ^ "The Visual Microphone". mit.edu.
- ^ Wu, Hao-Yu; Rubinstein, Michael; Shih, Eugene; Guttag, John; Durand, Frédo; Freeman, William (2012). "Eulerian video magnification for revealing subtle changes in the world". ACM Transactions on Graphics. 31 (4): 1–8. doi:10.1145/2185520.2185561.
- ^ "An algorithm for your blind spot | MIT CSAIL". mit.edu.
- ^ "Reach in and touch objects in videos with "Interactive Dynamic Video"". mit.edu. 2 August 2016.
- ^ https://halide-lang.org.
{{cite web}}
: Missing or empty|title=
(help) - ^ "Writing graphics software gets much easier". mit.edu. 2 August 2012.
- ^ "Writing Fast and Maintainable Code with Halide —The Pilot Episode". 24 April 2022.
- ^ "Symposium on Computational Photography and Video". mit.edu.
- ^ "ICCP 2009 News". mit.edu.
- ^ http://www.mpi-sb.mpg.de/~liegl/eg-awards/website/eg-awards_main.html.
{{cite web}}
: Missing or empty|title=
(help) - ^ "NSF Award Search: Award # 0447561 - CAREER: Transient Signal Processing for Realistic Imagery". nsf.gov.
- ^ "Microsoft Research – Emerging Technology, Computer, and Software Research". microsoft.com.
- ^ sloan.org http://www.sloan.org/programs/fellowshiplist.shtml.
{{cite web}}
: Missing or empty|title=
(help) - ^ siggraph.org http://s2016.siggraph.org/content/acm-siggraph-awards.
{{cite web}}
: Missing or empty|title=
(help)