We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

/pdf/microsoft-coco-common-objects-in-context-55ihxq1zt5.pdf

Microsoft COCO: Common Objects in Context

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

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F : Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

Unpaired Image-to-Image Translation Using Cycle-Consistent 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.

We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet.

/pdf/multi-view-stereo-for-community-photo-collections-30m43ntisv.pdf

Multi-View Stereo for Community Photo Collections

This paper presents a color structured light technique for recovering object shape from one or more images. The technique works by projecting a pattern of stripes of alternating colors and matching the projected color transitions with observed edges in the image. The correspondence problem is solved using a novel, multi-pass dynamic programming algorithm that eliminates global smoothness assumptions and strict ordering constraints present in previous formulations. The resulting approach is suitable for generating both high-speed scans of moving objects when projecting a single stripe pattern and high-resolution scans of static scenes using a short sequence of time-shifted stripe patterns. In the latter case, space-time analysis is used at each sensor pixel to obtain inter-frame depth localization. Results are demonstrated for a variety of complex scenes.

/pdf/rapid-shape-acquisition-using-color-structured-light-and-47540clupl.pdf

Rapid shape acquisition using color structured light and multi-pass dynamic programming

We present an end-to-end system that goes from video sequences to high resolution, editable, dynamically controllable face models. The capture system employs synchronized video cameras and structured light projectors to record videos of a moving face from multiple viewpoints. A novel spacetime stereo algorithm is introduced to compute depth maps accurately and overcome over-fitting deficiencies in prior work. A new template fitting and tracking procedure fills in missing data and yields point correspondence across the entire sequence without using markers. We demonstrate a data-driven, interactive method for inverse kinematics that draws on the large set of fitted templates and allows for posing new expressions by dragging surface points directly. Finally, we describe new tools that model the dynamics in the input sequence to enable new animations, created via key-framing or texture-synthesis techniques.

Spacetime faces: high resolution capture for modeling and animation

A surface light field is a function that assigns a color to each ray originating on a surface. Surface light fields are well suited to constructing virtual images of shiny objects under complex lighting conditions. This paper presents a framework for construction, compression, interactive rendering, and rudimentary editing of surface light fields of real objects. Generalization of vector quantization and principal component analysis are used to construct a compressed representation of an object's surface light field from photographs and range scans. A new rendering algorithm achieves interactive rendering of images from the compressed representation, incorporating view-dependent geometric level-of-detail control. The surface light field representation can also be directly edited to yield plausible surface light fields for small changes in surface geometry and reflectance properties.

/pdf/surface-light-fields-for-3d-photography-3j46e05upg.pdf

Surface light fields for 3D photography

We present a novel single image deblurring method to estimate spatially non-uniform blur that results from camera shake. We use existing spatially invariant deconvolution methods in a local and robust way to compute initial estimates of the latent image. The camera motion is represented as a Motion Density Function (MDF) which records the fraction of time spent in each discretized portion of the space of all possible camera poses. Spatially varying blur kernels are derived directly from the MDF. We show that 6D camera motion is well approximated by 3 degrees of motion (in-plane translation and rotation) and analyze the scope of this approximation. We present results on both synthetic and captured data. Our system out-performs current approaches which make the assumption of spatially invariant blur.

/pdf/single-image-deblurring-using-motion-density-functions-51js9f93s1.pdf

Brian Curless

Papers

Multi-View Stereo for Community Photo Collections

Rapid shape acquisition using color structured light and multi-pass dynamic programming

Spacetime faces: high resolution capture for modeling and animation

Surface light fields for 3D photography

Single image deblurring using motion density functions