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

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.

Fully Convolutional Networks for Semantic Segmentation

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous and causes issues. In this paper, we design a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input. Our network, named PointNet, provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Though simple, PointNet is highly efficient and effective. Empirically, it shows strong performance on par or even better than state of the art. Theoretically, we provide analysis towards understanding of what the network has learnt and why the network is robust with respect to input perturbation and corruption.

/pdf/pointnet-deep-learning-on-point-sets-for-3d-classification-1zge9sjodi.pdf

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

A survey on deep learning in medical image analysis

We propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on visual features - while running in real-time on a CPU. The key idea is to continuously estimate a semi-dense inverse depth map for the current frame, which in turn is used to track the motion of the camera using dense image alignment. More specifically, we estimate the depth of all pixels which have a non-negligible image gradient. Each estimate is represented as a Gaussian probability distribution over the inverse depth. We propagate this information over time, and update it with new measurements as new images arrive. In terms of tracking accuracy and computational speed, the proposed method compares favorably to both state-of-the-art dense and feature-based visual odometry and SLAM algorithms. As our method runs in real-time on a CPU, it is of large practical value for robotics and augmented reality applications.

/pdf/semi-dense-visual-odometry-for-a-monocular-camera-47oy5xn1wk.pdf

Semi-dense Visual Odometry for a Monocular Camera

We propose a novel direct sparse visual odometry formulation. It combines a fully direct probabilistic model (minimizing a photometric error) with consistent, joint optimization of all model parameters, including geometry -- represented as inverse depth in a reference frame -- and camera motion. This is achieved in real time by omitting the smoothness prior used in other direct methods and instead sampling pixels evenly throughout the images. Since our method does not depend on keypoint detectors or descriptors, it can naturally sample pixels from across all image regions that have intensity gradient, including edges or smooth intensity variations on mostly white walls. The proposed model integrates a full photometric calibration, accounting for exposure time, lens vignetting, and non-linear response functions. We thoroughly evaluate our method on three different datasets comprising several hours of video. The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness.

Direct Sparse Odometry

This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).

One-Shot Video Object Segmentation

We propose a novel Large-Scale Direct SLAM algorithm for stereo cameras (Stereo LSD-SLAM) that runs in real-time at high frame rate on standard CPUs. In contrast to sparse interest-point based methods, our approach aligns images directly based on the photoconsistency of all high-contrast pixels, including corners, edges and high texture areas. It concurrently estimates the depth at these pixels from two types of stereo cues: Static stereo through the fixed-baseline stereo camera setup as well as temporal multi-view stereo exploiting the camera motion. By incorporating both disparity sources, our algorithm can even estimate depth of pixels that are under-constrained when only using fixed-baseline stereo. Using a fixed baseline, on the other hand, avoids scale-drift that typically occurs in pure monocular SLAM.We furthermore propose a robust approach to enforce illumination invariance, capable of handling aggressive brightness changes between frames - greatly improving the performance in realistic settings. In experiments, we demonstrate state-of-the-art results on stereo SLAM benchmarks such as Kitti or challenging datasets from the EuRoC Challenge 3 for micro aerial vehicles.

/pdf/large-scale-direct-slam-with-stereo-cameras-2g8axvugex.pdf

Large-scale direct SLAM with stereo cameras

A look at the Middlebury optical flow benchmark [5] reveals that nowadays variational methods yield the most accurate optical flow fields between two image frames. In this work we propose an improvement variant of the original duality based TV-L 1 optical flow algorithm in [31] and provide implementation details. This formulation can preserve discontinuities in the flow field by employing total variation (TV) regularization. Furthermore, it offers robustness against outliers by applying the robust L 1 norm in the data fidelity term.

Our contributions are as follows. First, we propose to perform a structure-texture decomposition of the input images to get rid of violations in the optical flow constraint due to illumination changes. Second, we propose to integrate a median filter into the numerical scheme to further increase the robustness to sampling artefacts in the image data. We experimentally show that very precise and robust estimation of optical flow can be achieved with a variational approach in real-time. The numerical scheme and the implementation are described in a detailed way, which enables reimplementation of this high-end method.

/pdf/an-improved-algorithm-for-tv-l1-optical-flow-27urswxswb.pdf

Daniel Cremers

Papers

Semi-dense Visual Odometry for a Monocular Camera

Direct Sparse Odometry

One-Shot Video Object Segmentation

Large-scale direct SLAM with stereo cameras

An Improved Algorithm for TV-L1 Optical Flow