We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pix2pix software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without handengineering our loss functions either.

/pdf/image-to-image-translation-with-conditional-adversarial-5058t24et2.pdf

Image-to-Image Translation with Conditional Adversarial Networks

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Indeed, since the release of the pix2pix software associated with this paper, a large number of internet users (many of them artists) have posted their own experiments with our system, further demonstrating its wide applicability and ease of adoption without the need for parameter tweaking. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without hand-engineering our loss functions either.

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Titanium Dioxide Nanomaterials: Synthesis, Properties, Modifications, and Applications

Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can be easily extended to include new algorithms. We have also produced several new multiframe stereo data sets with ground truth, and are making both the code and data sets available on the Web.

/pdf/a-taxonomy-and-evaluation-of-dense-two-frame-stereo-4c20etkubp.pdf

A taxonomy and evaluation of dense two-frame stereo correspondence algorithms

Ultrafast All-Optical Switching and Modulation Using Intersubband Transitions in Coupled Quantum Well Structures (INVITED)

We propose a fully automatic approach to restore aged old line drawings. We decompose the task into two subtasks: the line extraction subtask, which aims to extract line fragments and remove the paper texture background, and the restoration subtask, which fills in possible gaps and deterioration of the lines to produce a clean line drawing. Our approach is based on a convolutional neural network that consists of two sub-networks corresponding to the two subtasks. They are trained as part of a single framework in an end-to-end fashion. We also introduce a new dataset consisting of manually annotated sketches by Leonardo da Vinci which, in combination with a synthetic data generation approach, allows training the network to restore deteriorated line drawings. We evaluate our method on challenging 500-year-old sketches and compare with existing approaches with a user study, in which it is found that our approach is preferred 72.7% of the time.

Learning to restore deteriorated line drawing

PURPOSE: To obtain a high performance semiconductor laser of low threshold current and to effectively amount on a heat sink by forming grooves having 10μm or less of surface width at both sides of the light emitting region of the laser, and flatly burying the groove with high resistance layers formed selectively by a vapor phase growing method such as a chloride vapor phase growing method, thereby suppressing a leakage current. CONSTITUTION: An N-type InP buffer layer 2, an InGaAsP active layer 3, a P-type InP clad layer 4 and P + type InGaAsP contact layer 5 are sequentially grown on an N-type InP substrate 1. An SiO 2 film 6 is accumulated, patterned to allow and SiO 2 film of the width (W 2 ) to remain on the light emitting region, and a hole of width (W 2 ) is formed. Then, with the film 6 as a mask a semiconductor crystal is etched to dig grooves 7. In this case, the size of the width W 1 of the groove is 10μm or less. Then, an InP high resistance layer is grown by chloride VPE to form a flat high resistance buried layer. Buried layers 8 formed at both sides of the active layer have 10 8 cm or higher to suppress the leakage current, thereby improving the characteristic such as threshold current. COPYRIGHT: (C)1986,JPO&Japio

Semiconductor light emitting device and manufacture thereof

A new stripe geometry GaAlAs double heterostructure laser with built‐in optical waveguide to stabilize the transverse mode parallel to the junction plane is developed. A novel optical waveguide and internal current confinement structure are realized in the structure. Lasers with strip width 4.7 μm and cavity length 200 μm showed cw threshold currents of 45–70 mA and highly stable transverse and longitudinal single‐mode lasing.

Mode‐stabilized separated multiclad layer stripe geometry GaAlAs double heterostructure laser

We propose a novel segmentation method based on energy minimization of higher-order potentials We introduce higher-order terms into the energy to incorporate prior knowledge on the shape of the segments The terms encourage certain sets of pixels to be entirely in one segment or the other The sets can for instance be smooth curves in order to help delineate pulmonary vessels, which are known to run in almost straight lines The higher-order terms can be converted to submodular first-order terms by adding auxiliary variables, which can then be globally minimized using graph cuts We also determine the weight of these terms, or the degree of the aforementioned encouragement, in a principled way by learning from training data with the ground truth We demonstrate the effectiveness of the method in a real-world application in fully-automatic pulmonary artery---vein segmentation in CT images

Hiroshi Ishikawa

Papers

Ultrafast All-Optical Switching and Modulation Using Intersubband Transitions in Coupled Quantum Well Structures (INVITED)

Learning to restore deteriorated line drawing

Semiconductor light emitting device and manufacture thereof

Mode‐stabilized separated multiclad layer stripe geometry GaAlAs double heterostructure laser

Data-Dependent Higher-Order Clique Selection for Artery---Vein Segmentation by Energy Minimization