Now showing items 1-20 of 21

    • Autotagging Facebook: Social Network Context Improves Photo Annotation 

      Stone, Zak; Zickler, Todd; Darrell, Trevor (Institute of Electrical & Electronics Engineers (IEEE), 2008)
      Most personal photos that are shared online are embedded in some form of social network, and these social networks are a potent source of contextual information that can be leveraged for automatic image understanding. In ...
    • Color Constancy Beyond Bags of Pixels 

      Chakrabarti, Ayan; Hirakawa, Keigo; Zickler, Todd (IEEE Computer Society Press, 2008)
      Estimating the color of a scene illuminant often plays a central role in computational color constancy. While this problem has received significant attention, the methods that exist do not maximally leverage spatial ...
    • Computational Color Constancy with Spatial Correlations 

      Chakrabarti, Ayan; Hirakawa, Keigo; Zickler, Todd (2010)
      The color of a scene recorded by a trichromatic sensor varies with the spectral distribution of the illuminant. For recognition and many other applications, we seek to process these measurements to obtain a color representation ...
    • Depth and Deblurring from a Spectrally-varying Depth-of-Field 

      Chakrabarti, Ayan; Zickler, Todd (Springer Verlag, 2012)
      We propose modifying the aperture of a conventional color camera so that the effective aperture size for one color channel is smaller than that for the other two. This produces an image where different color channels have ...
    • Discriminative virtual views for cross-view action recognition 

      Ruonan, Li; Zickler, Todd (IEEE, 2012)
      We propose an approach for cross-view action recognition by way of ‘virtual views’ that connect the action descriptors extracted from one (source) view to those extracted from another (target) view. Each virtual view is ...
    • A dynamic programming algorithm for perceptually consistent stereo 

      Wang, Jialiang; Glasner, Daniel; Zickler, Todd (2017-09-27)
      This document provides details of the dynamic programming algorithm discussed in “Towards perceptually consistent stereo: a scanline study." For the motivation of the algorithm, see that paper.
    • Ensemble Learning for Reectometry 

      Romeiro, Fabiano; Zickler, Todd (2010)
      In “Blind Reflectometry” (Romeiro and Zickler, 2010 [3]) we describe a variational Bayesian approach to inferring material properties (BRDF) from a single image of a known shape under unknown, real-world illumination. This ...
    • Face Identification in the Internet Era 

      Stone, Zachary (2013-02-11)
      Despite decades of effort in academia and industry, it is not yet possible to build machines that can replicate many seemingly-basic human perceptual abilities. This work focuses on the problem of face identification that ...
    • Fast Deconvolution with Color Constraints on Gradients 

      Chakrabarti, Ayan; Zickler, Todd (2012)
      In this report, we describe a fast deconvolution approach for color images that combines a sparse regularization cost on the magnitudes of gradients with constraints on their direction in color space. We form these color ...
    • Finding Group Interactions in Social Clutter 

      Li, Ruonan; Porfilio, Parker; Zickler, Todd (2013)
      We consider the problem of finding distinctive social interactions involving groups of agents embedded in larger social gatherings. Given a pre-defined gallery of short exemplar interaction videos, and a long input video ...
    • Focal Flow: Supporting material 

      Alexander, Emma; Guo, Enrique; Koppal, S.J.; Gortler, Steven J.; Zickler, Todd (2016)
    • From Pixels to Physics: Probabilistic Color De-Rendering 

      Xiong, Ying; Saenko, K.; Darrell, T.; Zickler, Todd (IEEE, 2012)
      Consumer digital cameras use tone-mapping to produce compact, narrow-gamut images that are nonetheless visually pleasing. In doing so, they discard or distort substantial radiometric signal that could otherwise be used for ...
    • Inferring Reflectance under Real-world Illumination 

      Romeiro, Fabiano; Zickler, Todd (2010)
      We address the problem of inferring homogeneous reflectance (BRDF) from a single image of a known shape in an unknown real-world lighting environment. With appropriate representations of lighting and reflectance, the image ...
    • Modeling the Uncertainty in Inverse Radiometric Calibration 

      Xiong, Ying; Saenko, Kate; Zickler, Todd; Darrell, Trevor (2011)
      While the color image formats used by modern cameras provide visually pleasing images, they distort and discard a significant amount of signal that is useful for many applications. Existing methods for modeling physical ...
    • A Perception-based Color Space for Illumination-invariant Image Processing 

      Chong, Hamilton; Gortler, Steven; Zickler, Todd (Association for Computing Machinery, 2008)
      Motivated by perceptual principles, we derive a new color space in which the associated metric approximates perceived distances and color displacements capture relationships that are robust to spectral changes in illumination. ...
    • Photometric Stereo with Non-Parametric and Spatially-Varying Reflectance 

      Zickler, Todd; Alldrin, Neil; Kriegman, David (IEEE Computer Society Press, 2008)
      We present a method for simultaneously recovering shape and spatially varying reflectance of a surface from photometric stereo images. The distinguishing feature of our approach is its generality; it does not rely on a ...
    • Physics-Based Visual Inference: Theory and Applications 

      Xiong, Ying (2015-08-27)
      Analyzing images to infer physical scene properties is a fundamental task in computer vision. It is by nature an ill-posed inverse problem, because imaging is a complicated, information-lossy physical and measurement process ...
    • Toward Shape from a Single Specular Flow 

      Vasilyev, Yuriy; Zickler, Todd; Gortler, Steven J.; Ben-Shahar, Ohad (2011)
      In “Shape From Specular Flow: Is One Flow Enough?” (Vasilyev, et al., 2011 [5]) we show that mirror shape can often be reconstructed from the observation of a single specular flow. In this technical report we provide ...
    • Unique specular shape from two specular flows 

      Canas, Guillermo D.; Vasilyev, Yuriy; Adato, Yair; Zickler, Todd; Gortler, Steven J.; Ben-Shahar, Ohad (2009)
      When a curved mirror-like surface moves relative to its environment, it induces a motion field—or specular flow—on the image plane that observes it. This specular flow is related to the mirror’s shape through a non-linear ...
    • The von Kries hypothesis and a basis for color constancy 

      Chong, Hamilton; Gortler, Steven; Zickler, Todd (Institute of Electrical and Electronics Engineers (IEEE), 2007)
      Color constancy is almost exclusively modeled with diagonal transforms. However, the choice of basis under which diagonal transforms are taken is traditionally ad hoc. Attempts to remedy the situation have been hindered ...