Person: Zickler, Todd
Loading...
Email Address
AA Acceptance Date
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
Zickler
First Name
Todd
Name
Zickler, Todd
22 results
Search Results
Now showing 1 - 10 of 22
Publication Discriminative virtual views for cross-view action recognition(IEEE, 2012) Ruonan, Li; Zickler, ToddWe 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 associated with a linear transformation of the action descriptor, and the sequence of transformations arising from the sequence of virtual views aims at bridging the source and target views while preserving discrimination among action categories. Our approach is capable of operating without access to labeled action samples in the target view and without access to corresponding action instances in the two views, and it also naturally incorporate and exploit corresponding instances or partial labeling in the target view when they are available. The proposed approach achieves improved or competitive performance relative to existing methods when instance correspondences or target labels are available, and it goes beyond the capabilities of these methods by providing some level of discrimination even when neither correspondences nor target labels exist.Publication From Pixels to Physics: Probabilistic Color De-Rendering(IEEE, 2012) Xiong, Ying; Saenko, K.; Darrell, T.; Zickler, ToddConsumer 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 computer vision. Existing methods attempt to undo these effects through deterministic maps that de-render the reported narrow-gamut colors back to their original wide-gamut sensor measurements. Deterministic approaches are unreliable, however, because the reverse narrow-to-wide mapping is one-to-many and has inherent uncertainty. Our solution is to use probabilistic maps, providing uncertainty estimates useful to many applications. We use a non-parametric Bayesian regression technique - local Gaussian process regression - to learn for each pixel's narrow-gamut color a probability distribution over the scene colors that could have created it. Using a variety of consumer cameras we show that these distributions, once learned from training data, are effective in simple probabilistic adaptations of two popular applications: multi-exposure imaging and photometric stereo. Our results on these applications are better than those of corresponding deterministic approaches, especially for saturated and out-of-gamut colors.Publication Depth and Deblurring from a Spectrally-varying Depth-of-Field(Springer Verlag, 2012) Chakrabarti, Ayan; Zickler, ToddWe 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 different depths-of-field, and from this we can computationally recover scene depth, reconstruct an all-focus image and achieve synthetic re-focusing, all from a single shot. These capabilities are enabled by a spatio-spectral image model that encodes the statistical relationship between gradient profiles across color channels. This approach substantially improves depth accuracy over alternative single-shot coded-aperture designs, and since it avoids introducing additional spatial distortions and is light efficient, it allows high-quality deblurring and lower exposure times. We demonstrate these benefits with comparisons on synthetic data, as well as results on images captured with a prototype lens.Publication Unique specular shape from two specular flows(2009) Canas, Guillermo D.; Vasilyev, Yuriy; Adato, Yair; Zickler, Todd; Gortler, Steven; Ben-Shahar, OhadWhen 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 partial differential equation, and there is interest in understanding when and how this equation can be solved for surface shape. Existing analyses of this ‘shape from specular flow equation’ have focused on closed-form solutions, and while they have yielded insight, their critical reliance on externally-provided initial conditions and/or specific motions makes them difficult to apply in practice. This paper resolves these issues. We show that a suitable reparameterization leads to a linear formulation of the shape from specular flow equation. This formulation radically simplifies the reconstruction process and allows, for example, both motion and shape to be recovered from as few as two specular flows even when no externally-provided initial conditions are available. The result of our analysis is a practical method for recovering shape from specular flow that operates under arbitrary, unknown motions in unknown illumination environments and does not require additional shape information from other sources.Publication Ensemble Learning for Reectometry(2010) Romeiro, Fabiano; Zickler, ToddIn “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 technical report provides additional details of that approach. First, we detail the prior probability distribution for natural lighting environments. Second, we provide a derivation of the bilinear likelihood expression that is based on discretizing the rendering equation. Third and finally, we provide the update equations for the iterative algorithm that computes an approximation to the posterior distribution of BRDFs.Publication Fast Deconvolution with Color Constraints on Gradients(2012) Chakrabarti, Ayan; Zickler, ToddIn 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 constraints in a way that allows retaining the computationally-efficient optimization strategy introduced in recent deconvolution methods based on half-quadratic splitting. The proposed algorithm is capable of handling a different blur kernel in each color channel, and is used for per-layer deconvolution in our paper: “Depth and Deblurring from a Spectrally-varying Depth-of-Field." A MATLAB implementation of this method is available at http://vision.seas.harvard.edu/ccap, and takes roughly 20 seconds to deconvolve a three-channel 1544 × 1028 color image, on a Linux-based Intel I-3 2.1GHz machine.Publication Inferring Reflectance under Real-world Illumination(2010) Romeiro, Fabiano; Zickler, ToddWe 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 provides bilinear constraints on the two signals, and our task is to blindly isolate the latter. We achieve this by leveraging the statistics of real-world illumination and estimating the reflectance that is most likely under a distribution of probable illumination environments. Experimental results suggest that useable reflectance information can be often be inferred, and that these estimates are stable under changes in lighting.Publication Focal Flow: Measuring Distance and Velocity with Defocus and Differential Motion(Springer International Publishing, 2016) Alexander, Emma; Guo, Qi; Koppal, Sanjeev; Gortler, Steven; Zickler, ToddWe present the focal flow sensor. It is an unactuated, monocular camera that simultaneously exploits defocus and differential motion to measure a depth map and a 3D scene velocity field. It does so using an optical-flow-like, per-pixel linear constraint that relates image derivatives to depth and velocity. We derive this constraint, prove its invariance to scene texture, and prove that it is exactly satisfied only when the sensor’s blur kernels are Gaussian. We analyze the inherent sensitivity of the ideal focal flow sensor, and we build and test a prototype. Experiments produce useful depth and velocity information for a broader set of aperture configurations, including a simple lens with a pillbox aperture.Publication Modeling the Uncertainty in Inverse Radiometric Calibration(2011) Xiong, Ying; Saenko, Kate; Zickler, Todd; Darrell, TrevorWhile 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 world properties based on such narrow-gamut images use a deterministic, per-channel, one-to-one mapping to get back to wide-gamut physical scene colors, ignoring the uncertainty inherent in the process. Rather than fit a deterministic parametric model, we show that non-parametric Bayesian regression techniques, e.g. Gaussian Processes (GP), are well-suited to model this de-rendering process, and accurately capture the uncertainty in the transformation. We propose a probabilistic approach that outputs, for each low-gamut image color, a distribution over the wide-gamut scene colors that could have created it. Using a variety of different consumer camera models, we show that effective distributions can be learned by online local Gaussian process regression. Such distributions can be used to hallucinate estimates of RAW values corresponding to JPEG samples, creating “out-of-gamut” images, and also to improve robustness in related applications, e.g., when recovering three-dimensional shape via photometric stereo.Publication Focal Flow: Supporting material(2016) Alexander, Emma; Guo, Qi; Koppal, S.J.; Gortler, Steven; Zickler, Todd
- «
- 1 (current)
- 2
- 3
- »