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

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti

/pdf/are-we-ready-for-autonomous-driving-the-kitti-vision-zygefho352.pdf

Are we ready for autonomous driving? The KITTI vision benchmark suite

In this paper, we propose a novel explicit image filter called guided filter. Derived from a local linear model, the guided filter computes the filtering output by considering the content of a guidance image, which can be the input image itself or another different image. The guided filter can be used as an edge-preserving smoothing operator like the popular bilateral filter [1], but it has better behaviors near edges. The guided filter is also a more generic concept beyond smoothing: It can transfer the structures of the guidance image to the filtering output, enabling new filtering applications like dehazing and guided feathering. Moreover, the guided filter naturally has a fast and nonapproximate linear time algorithm, regardless of the kernel size and the intensity range. Currently, it is one of the fastest edge-preserving filters. Experiments show that the guided filter is both effective and efficient in a great variety of computer vision and computer graphics applications, including edge-aware smoothing, detail enhancement, HDR compression, image matting/feathering, dehazing, joint upsampling, etc.

/pdf/guided-image-filtering-5atmpsksoa.pdf

Guided Image Filtering

This paper describes the semiglobal matching (SGM) stereo method. It uses a pixelwise, mutual information (Ml)-based matching cost for compensating radiometric differences of input images. Pixelwise matching is supported by a smoothness constraint that is usually expressed as a global cost function. SGM performs a fast approximation by pathwise optimizations from all directions. The discussion also addresses occlusion detection, subpixel refinement, and multibaseline matching. Additionally, postprocessing steps for removing outliers, recovering from specific problems of structured environments, and the interpolation of gaps are presented. Finally, strategies for processing almost arbitrarily large images and fusion of disparity images using orthographic projection are proposed. A comparison on standard stereo images shows that SGM is among the currently top-ranked algorithms and is best, if subpixel accuracy is considered. The complexity is linear to the number of pixels and disparity range, which results in a runtime of just 1-2 seconds on typical test images. An in depth evaluation of the Ml-based matching cost demonstrates a tolerance against a wide range of radiometric transformations. Finally, examples of reconstructions from huge aerial frame and pushbroom images demonstrate that the presented ideas are working well on practical problems.

/pdf/stereo-processing-by-semiglobal-matching-and-mutual-147l7nvp3i.pdf

Stereo Processing by Semiglobal Matching and Mutual Information

The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: (1) sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture, (2) realistic synthetic sequences, (3) high frame-rate video used to study interpolation error, and (4) modified stereo sequences of static scenes. In addition to the average angular error used by Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and results at motion discontinuities and in textureless regions. In October 2007, we published the performance of several well-known methods on a preliminary version of our data to establish the current state of the art. We also made the data freely available on the web at http://vision.middlebury.edu/flow/ . Subsequently a number of researchers have uploaded their results to our website and published papers using the data. A significant improvement in performance has already been achieved. In this paper we analyze the results obtained to date and draw a large number of conclusions from them.

/pdf/a-database-and-evaluation-methodology-for-optical-flow-2numl3kx6v.pdf

A Database and Evaluation Methodology for Optical Flow

Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge preserving filter. In this paper we propose a generic and simple framework comprising three steps: (i) constructing a cost volume (ii) fast cost volume filtering and (iii) winner-take-all label selection. Our main contribution is to show that with such a simple framework state-of-the-art results can be achieved for several computer vision applications. In particular, we achieve (i) disparity maps in real-time, whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and (ii) optical flow fields with very fine structures as well as large displacements. To demonstrate robustness, the few parameters of our framework are set to nearly identical values for both applications. Also, competitive results for interactive image segmentation are presented. With this work, we hope to inspire other researchers to leverage this framework to other application areas.

/pdf/fast-cost-volume-filtering-for-visual-correspondence-and-51f012gcat.pdf

Fast cost-volume filtering for visual correspondence and beyond

Common local stereo methods match support windows at integer-valued disparities. The implicit assumption that pixels within the support region have constant disparity does not hold for slanted surfaces and leads to a bias towards reconstructing frontoparallel surfaces. This work overcomes this bias by estimating an individual 3D plane at each pixel onto which the support region is projected. The major challenge of this approach is to find a pixel’s optimal 3D plane among all possible planes whose number is infinite. We show that an ideal algorithm to solve this problem is PatchMatch [1] that we extend to find an approximate nearest neighbor according to a plane. In addition to Patch-Match’s spatial propagation scheme, we propose (1) view propagation where planes are propagated among left and right views of the stereo pair and (2) temporal propagation where planes are propagated from preceding and consecutive frames of a video when doing temporal stereo. Adaptive support weights are used in matching cost aggregation to improve results at disparity borders. We also show that our slanted support  windows can be used to compute a cost volume for global stereo methods, which allows for explicit treatment of occlusions and can handle large untextured regions. In the results we demonstrate that our method reconstructs highly slanted surfaces and achieves impressive disparity details with sub-pixel precision. In the Middlebury table, our method is currently top-performer among local methods and takes rank 2 among approximately 110 competitors if sub-pixel precision is considered.

/pdf/patchmatch-stereo-stereo-matching-with-slanted-support-2an0b4lo8h.pdf

PatchMatch Stereo - Stereo Matching with Slanted Support Windows.

Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge-preserving filter. In this paper, we propose a generic and simple framework comprising three steps: 1) constructing a cost volume, 2) fast cost volume filtering, and 3) Winner-Takes-All label selection. Our main contribution is to show that with such a simple framework state-of-the-art results can be achieved for several computer vision applications. In particular, we achieve 1) disparity maps in real time whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and 2) optical flow fields which contain very fine structures as well as large displacements. To demonstrate robustness, the few parameters of our framework are set to nearly identical values for both applications. Also, competitive results for interactive image segmentation are presented. With this work, we hope to inspire other researchers to leverage this framework to other application areas.

/pdf/fast-cost-volume-filtering-for-visual-correspondence-and-1d9o8ipfcd.pdf

Fast Cost-Volume Filtering for Visual Correspondence and Beyond

Local stereo matching has recently experienced large progress by the introduction of new support aggregation schemes. These approaches estimate a pixel's support region via color segmentation. Our contribution lies in an improved method for accomplishing this segmentation. Inside a square support window, we compute the geodesic distance from all pixels to the window's center pixel. Pixels of low geodesic distance are given high support weights and therefore large influence in the matching process. In contrast to previous work, we enforce connectivity by using the geodesic distance transform. For obtaining a high support weight, a pixel must have a path to the center point along which the color does not change significantly. This connectivity property leads to improved segmentation results and consequently to improved disparity maps. The success of our geodesic approach is demonstrated on the Middlebury images. According to the Middlebury benchmark, the proposed algorithm is the top performer among local stereo methods at the current state-of-the-art.

/pdf/local-stereo-matching-using-geodesic-support-weights-3d07igzdza.pdf

Local stereo matching using geodesic support weights

This paper presents a method for joint stereo matching and object segmentation. In our approach a 3D scene is represented as a collection of visually distinct and spatially coherent objects. Each object is characterized by three different aspects: a color model, a 3D plane that approximates the object's disparity distribution, and a novel 3D connectivity property. Inspired by Markov Random Field models of image segmentation, we employ object-level color models as a soft constraint, which can aid depth estimation in powerful ways. In particular, our method is able to recover the depth of regions that are fully occluded in one input view, which to our knowledge is new for stereo matching. Our model is formulated as an energy function that is optimized via fusion moves. We show high-quality disparity and object segmentation results on challenging image pairs as well as standard benchmarks. We believe our work not only demonstrates a novel synergy between the areas of image segmentation and stereo matching, but may also inspire new work in the domain of automatic and interactive object-level scene manipulation.

/pdf/object-stereo-joint-stereo-matching-and-object-segmentation-iavyexk2ox.pdf

Michael Bleyer

Papers

Fast cost-volume filtering for visual correspondence and beyond

PatchMatch Stereo - Stereo Matching with Slanted Support Windows.

Fast Cost-Volume Filtering for Visual Correspondence and Beyond

Local stereo matching using geodesic support weights

Object stereo — Joint stereo matching and object segmentation