Difference between revisions of "3D Form and Motion"

From RedwoodCenter
Jump to navigationJump to search
 
(22 intermediate revisions by the same user not shown)
Line 7: Line 7:
 
* Cashman and Fitzgibbon: "What Shape are Dolphins? Building 3D Morphable Models from 2D Images" [http://redwood.berkeley.edu/bruno/3DFM/cashman-fitzgibbon.pdf pdf]
 
* Cashman and Fitzgibbon: "What Shape are Dolphins? Building 3D Morphable Models from 2D Images" [http://redwood.berkeley.edu/bruno/3DFM/cashman-fitzgibbon.pdf pdf]
 
* Snavely and Seitz (2006), "Photo tourism" (aka photosynth), [http://redwood.berkeley.edu/bruno/3DFM/snavely-seitz.pdf pdf]
 
* Snavely and Seitz (2006), "Photo tourism" (aka photosynth), [http://redwood.berkeley.edu/bruno/3DFM/snavely-seitz.pdf pdf]
 +
* Seitz google talk on history of 3D computer vision: [https://www.youtube.com/watch?v=kyIzMr917Rc URL]
 +
** Blanz and Vetter, 3D face models [http://redwood.berkeley.edu/bruno/3DFM/Blanz-siggraph-99.pdf pdf]
 +
** Tomasi and Kanade, factorization of shape and motion, [http://redwood.berkeley.edu/bruno/3DFM/TomasiKanade92.pdf pdf]
 +
* Blanz & Vetter (2003) "Face Recognition Based on Fitting a 3D Morphable Model" [http://redwood.berkeley.edu/bruno/3DFM/Blanz-vetter-IEEE2003.pdf pdf]
 +
* Atick & Redlich papers:
 +
** "The vocabulary of shape: principal shapes for probing perception and neural response" [http://redwood.berkeley.edu/bruno/3DFM/atick-redlich-vocabulary.pdf pdf]
 +
** "Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images" [http://redwood.berkeley.edu/bruno/3DFM/atick-redlich-shape-from-shading.pdf pdf]
 +
* Bregler, Hertzmann, "Recovering non-rigid 3D shape from image streams" [http://redwood.berkeley.edu/bruno/3DFM/bregler-hertzmann.pdf pdf]
 +
* Allen, Curless, Popovic, "The space of human body shapes: reconstruction and parameterization from range scans" [http://redwood.berkeley.edu/bruno/3DFM/curless-body-shape.pdf pdf]
 +
* Suggested by Pulkit:
 +
** D Ramanan, "Analyzing 3D Objects in Cluttered Images" [http://www.ics.uci.edu/~dramanan/papers/car.pdf pdf]
 +
** B Schiele, first couple of papers at [http://www.d2.mpi-inf.mpg.de/publications url]
 +
* Gal et al., "Local shape priors" [http://www.cs.jhu.edu/~misha/ReadingSeminar/Papers/Gal07.pdf pdf]
 +
* Jon Barron's papers [http://www.cs.berkeley.edu/~barron/ url]
 +
** TPAMI [http://redwood.berkeley.edu/bruno/3DFM/Barron-TPAMI.pdf preprint]
 +
* Pentland, "A Possible Neural Mechanism for Computing Shape From Shading" [http://redwood.berkeley.edu/bruno/3DFM/pentland-shape-from-shading.pdf pdf]
 +
 +
'''Kinect'''
 +
* KinectFusion [http://www.youtube.com/watch?v=quGhaggn3cQ&sns=em demo]
 +
** UIST 2011 paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion.pdf pdf]
 +
** IEEE conf paper [http://redwood.berkeley.edu/bruno/3DFM/kinect-fusion-IEEE.pdf pdf]
 +
 +
'''3D data sets'''
 +
* Princeton Shape data set:  [http://shape.cs.princeton.edu/benchmark/ url]
 +
* Ponce: [http://www-cvr.ai.uiuc.edu/ponce_grp/data/ url]
 +
* Silberman [http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html url]
  
 
'''SLAM:'''
 
'''SLAM:'''
Line 12: Line 38:
 
* Thrun, "Probabilistic algorithms in robotics" [http://redwood.berkeley.edu/bruno/3DFM/thrun-SLAM.pdf pdf]
 
* Thrun, "Probabilistic algorithms in robotics" [http://redwood.berkeley.edu/bruno/3DFM/thrun-SLAM.pdf pdf]
 
* Daniel Cremers work on helicopters/SLAM (TU Munich) [http://vision.in.tum.de/research URL]
 
* Daniel Cremers work on helicopters/SLAM (TU Munich) [http://vision.in.tum.de/research URL]
 +
* Davison references on monocular SLAM [http://www.doc.ic.ac.uk/%7Eajd/publications.html URL]
 
* Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", [http://redwood.berkeley.edu/bruno/3DFM/newcombe-davison.pdf pdf]
 
* Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", [http://redwood.berkeley.edu/bruno/3DFM/newcombe-davison.pdf pdf]
  
Line 18: Line 45:
 
* Glennerster and Fitzgibbon, "View-Based Approaches to Spatial Representation in Human Vision" [http://redwood.berkeley.edu/bruno/3DFM/glennerster-fitzgibbon.pdf pdf]
 
* Glennerster and Fitzgibbon, "View-Based Approaches to Spatial Representation in Human Vision" [http://redwood.berkeley.edu/bruno/3DFM/glennerster-fitzgibbon.pdf pdf]
 
* Wexler work on depth from self-motion/parallax, reference frames, [http://redwood.berkeley.edu/bruno/3DFM/wexler-droulez.pdf pdf1], [http://redwood.berkeley.edu/bruno/3DFM/Psychological_Science-2003-Wexler-340-6.pdf pdf2]
 
* Wexler work on depth from self-motion/parallax, reference frames, [http://redwood.berkeley.edu/bruno/3DFM/wexler-droulez.pdf pdf1], [http://redwood.berkeley.edu/bruno/3DFM/Psychological_Science-2003-Wexler-340-6.pdf pdf2]
 +
 +
'''Action-perception:'''
 +
* Philipona et al. Neural Computation (2003)  [http://redwood.berkeley.edu/bruno/3DFM/Philipona-NC03.pdf pdf]
 +
** Follow on papers [http://scholar.google.com/scholar?cites=12668418378270464515&as_sdt=2005&sciodt=0,5&hl=en URL]
 +
* Philipona et al. NIPS (2003) [http://redwood.berkeley.edu/bruno/3DFM/Philipona-NIPS03.pdf pdf]
 +
** Follow on papers [http://scholar.google.com/scholar?cites=2694340780306411921&as_sdt=2005&sciodt=0,5&hl=en URL]
 +
* Polani et al. "From unknown sensors and actuators to actions" [http://redwood.berkeley.edu/bruno/3DFM/polani-robot.pdf pdf]
 +
* Robotics paper trying to perceive environment based on sensiromotor loop (from Pulkit): [http://www.aaai.org/Papers/AAAI/2007/AAAI07-174.pdf pdf]
 +
 +
'''Eye movements:'''
 +
* Glennerster et al. (2001) "Fixation could simplify, not complicate, the interpretation of retinal flow" [http://redwood.berkeley.edu/bruno/3DFM/glennerster-fixation.pdf pdf]
 +
* Daniilidis, K. (1997)  "Fixation simplifies 3D motion estimation."  Computer Vision and Image Understanding, 68(2), 158--169.
 +
 +
'''Manifolds:'''
 +
* Manifolds in computer vision tutorial: [http://redwood.berkeley.edu/bruno/3DFM/manifolds.pdf pdf]
 +
** references: [http://www.cs.fsu.edu/~liux/manifold-short-course/reference.html URL]

Latest revision as of 23:06, 15 September 2013

Mondays at 1:00, Evans 560

3D models from images:

  • Hartley and Zisserman: Multiple View Geometry (Amazon)
  • Hoiem and Savarese: 3D object recognition and scene interpretation, book pdf
  • Hoiem Ph.D. thesis "SEEING THE WORLD BEHIND THE IMAGE" pdf
  • Cashman and Fitzgibbon: "What Shape are Dolphins? Building 3D Morphable Models from 2D Images" pdf
  • Snavely and Seitz (2006), "Photo tourism" (aka photosynth), pdf
  • Seitz google talk on history of 3D computer vision: URL
    • Blanz and Vetter, 3D face models pdf
    • Tomasi and Kanade, factorization of shape and motion, pdf
  • Blanz & Vetter (2003) "Face Recognition Based on Fitting a 3D Morphable Model" pdf
  • Atick & Redlich papers:
    • "The vocabulary of shape: principal shapes for probing perception and neural response" pdf
    • "Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images" pdf
  • Bregler, Hertzmann, "Recovering non-rigid 3D shape from image streams" pdf
  • Allen, Curless, Popovic, "The space of human body shapes: reconstruction and parameterization from range scans" pdf
  • Suggested by Pulkit:
    • D Ramanan, "Analyzing 3D Objects in Cluttered Images" pdf
    • B Schiele, first couple of papers at url
  • Gal et al., "Local shape priors" pdf
  • Jon Barron's papers url
  • Pentland, "A Possible Neural Mechanism for Computing Shape From Shading" pdf

Kinect

  • KinectFusion demo
    • UIST 2011 paper pdf
    • IEEE conf paper pdf

3D data sets

  • Princeton Shape data set: url
  • Ponce: url
  • Silberman url

SLAM:

  • wiki page with list of refs
  • Thrun, "Probabilistic algorithms in robotics" pdf
  • Daniel Cremers work on helicopters/SLAM (TU Munich) URL
  • Davison references on monocular SLAM URL
  • Newcombe and Davison, "Live dense reconstruction with a single moving camera work on fast single camera", pdf

Psychophysics:

  • Nakayama et al. (1995) "Visual Surface Representation" pdf
  • Glennerster and Fitzgibbon, "View-Based Approaches to Spatial Representation in Human Vision" pdf
  • Wexler work on depth from self-motion/parallax, reference frames, pdf1, pdf2

Action-perception:

  • Philipona et al. Neural Computation (2003) pdf
    • Follow on papers URL
  • Philipona et al. NIPS (2003) pdf
    • Follow on papers URL
  • Polani et al. "From unknown sensors and actuators to actions" pdf
  • Robotics paper trying to perceive environment based on sensiromotor loop (from Pulkit): pdf

Eye movements:

  • Glennerster et al. (2001) "Fixation could simplify, not complicate, the interpretation of retinal flow" pdf
  • Daniilidis, K. (1997) "Fixation simplifies 3D motion estimation." Computer Vision and Image Understanding, 68(2), 158--169.

Manifolds:

  • Manifolds in computer vision tutorial: pdf
    • references: URL