Show simple item record

dc.contributor.advisorFrédo Durand.en_US
dc.contributor.authorLo, Tzu-Maoen_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.en_US
dc.date.accessioned2019-10-11T21:14:38Z
dc.date.available2019-10-11T21:14:38Z
dc.date.copyright2019en_US
dc.date.issued2019en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/122486
dc.descriptionThis electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.en_US
dc.descriptionThesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019en_US
dc.descriptionCataloged from student-submitted PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 131-148).en_US
dc.description.abstractDerivatives of computer graphics, image processing, and deep learning algorithms have tremendous use in guiding parameter space searches, or solving inverse problems. As the algorithms become more sophisticated, we no longer only need to differentiate simple mathematical functions, but have to deal with general programs which encode complex transformations of data. This dissertation introduces three tools, for addressing the challenges that arise when obtaining and applying the derivatives for complex graphics algorithms. Traditionally, practitioners have been constrained to composing programs with a limited set of coarse-grained operators, or hand-deriving derivatives. We extend the image processing language Halide with reverse-mode automatic differentiation, and the ability to automatically optimize the gradient computations. This enables automatic generation of the gradients of arbitrary Halide programs, at high performance, with little programmer effort.en_US
dc.description.abstractWe demonstrate several applications, including how our system enables quality improvements of even traditional, feed-forward image processing algorithms, blurring the distinction between classical and deep learning methods. In 3D rendering, the gradient is required with respect to variables such as camera parameters, light sources, geometry, and appearance. However, computing the gradient is challenging because the rendering integral includes visibility terms that are not differentiable. We introduce, to our knowledge, the first general-purpose differentiable ray tracer that solves the full rendering equation, while correctly taking the geometric discontinuities into account. We show prototype applications in inverse rendering and the generation of adversarial examples for neural networks. Finally, we demonstrate that the derivatives of light path throughput, especially the second-order ones, can also be useful for guiding sampling in forward rendering.en_US
dc.description.abstractSimulating light transport in the presence of multi-bounce glossy effects and motion in 3D rendering is challenging due to the high-dimensional integrand and narrow high-contribution areas. We extend the Metropolis Light Transport algorithm by adapting to the local shape of the integrand, thereby increasing sampling efficiency. In particular, the Hessian is able to capture the strong anisotropy of the integrand. We use ideas from Hamiltonian Monte Carlo and simulate physics in Taylor expansion to draw samples from high-contribution region.en_US
dc.description.statementofresponsibilityby Tzu-Mao Lo.en_US
dc.format.extent148 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectElectrical Engineering and Computer Science.en_US
dc.titleDifferentiable visual computingen_US
dc.typeThesisen_US
dc.description.degreePh. D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.identifier.oclc1122780012en_US
dc.description.collectionPh.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienceen_US
dspace.imported2019-10-11T21:14:37Zen_US
mit.thesis.degreeDoctoralen_US
mit.thesis.departmentEECSen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record