In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for different application scenarios. Moreover, most monocular systems suffer from scale-drift issue. Some recent deep learning works learn VO in an end-to-end manner but the performance of these deep systems is still not comparable to geometry-based methods. In this work, we revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point (PnP) method. Specifically, we train two convolutional neural networks (CNNs) for estimating single-view depths and two-view optical flows as intermediate outputs. With the deep predictions, we design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods. More importantly, our system does not suffer from the scale-drift issue being aided by a scale consistent single-view depth CNN. Extensive experiments on KITTI dataset shows the robustness of our system and a detailed ablation study shows the effect of different factors in our system. Code is available at here: DF-VO.

In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image. In contrast to most existing frameworks which represent outdoor scenes as fronto-parallel planes at piece-wise smooth depth, we propose to predict depth with surface orientation while assuming that natural scenes have piece-wise smooth normals. We show that a simple depth-normal consistency as a soft-constraint on the predictions is sufficient and effective for training both these networks simultaneously. The trained normal network provides state-of-the-art predictions while the depth network, relying on much realistic smooth normal assumption, outperforms the traditional self-supervised depth prediction network by a large margin on the KITTI benchmark.

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to ambiguous matches in texture-less regions when performing dense reconstruction due to the aperture problem. In this work, we explore the use of learned features for the matching task in dense monocular reconstruction. We propose a novel convolutional neural network (CNN) architecture along with a deeply supervised feature learning scheme for pixel-wise regression of visual descriptors from an image which are best suited for dense monocular SLAM. In particular, our learning scheme minimizes a multi-view matching cost-volume loss with respect to the regressed features at multiple stages within the network, for explicitly learning contextual features that are suitable for dense matching between images captured by a moving monocular camera along the epipolar line. We integrate the learned features from our model for depth estimation inside a real-time dense monocular SLAM framework, where photometric error is replaced by our learned descriptor error. Our extensive evaluation on several challenging indoor datasets demonstrate greatly improved accuracy in dense reconstructions of the well celebrated dense SLAM systems like DTAM, without compromising their real-time performance.

We propose a method for learning a scene coordinate regression model to perform accurate camera relocalization in a known environment from a single RGB image. Our method incorporates self-supervision for scene coordinates via multi-view geometric constraints to improve training. More specifically, we use an image-based warp error between different views of a scene point to improve the ability of the network to regress to the correct absolute scene coordinates of the point. For the warp error we explore both RGB values, and deep learned features, as the basis for the error. We provide a thorough analysis of the effect of each component in our framework and evaluate our method on both indoor and outdoor datasets. We show that compared to the coordinate regression model trained with single-view information, this multi-view constraint benefits the learning process and the final performance. It not only helps the networks converge faster compared to the model trained with single-view reprojection loss, but also improves the accuracy of the absolute pose estimation using a single RGB image compared to the prior art.

We present "just-in-time reconstruction" as realtime image-guided inpainting of a map with arbitrary scale and sparsity to generate a fully dense depth map for the image. In particular, our goal is to inpaint a sparse map - obtained from either a monocular visual SLAM system or a sparse sensor - using a single-view depth prediction network as a virtual depth sensor. We adopt a fairly standard approach to data fusion, to produce a fused depth map by performing inference over a novel fully-connected Conditional Random Field (CRF) which is parameterized by the input depth maps and their pixel-wise confidence weights. Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image. Our CRF model penalises absolute depth error in its nodes and pairwise scale-invariant depth error in its edges, and the confidence-based fusion minimizes the impact of outlier input depth values on the fused result. We demonstrate the flexibility of our method by real-time inpainting of ORB-SLAM, Kinect, and LIDAR depth maps acquired both indoors and outdoors at arbitrary scale and varied amount of irregular sparsity.

Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner. Recent approaches to single view depth estimation explore the possibility of learning without full supervision via minimizing photometric error. In this paper, we explore the use of stereo sequences for learning depth and visual odometry. The use of stereo sequences enables the use of both spatial (between left-right pairs) and temporal (forward backward) photometric warp error, and constrains the scene depth and camera motion to be in a common, real-world scale. At test time our framework is able to estimate single view depth and two-view odometry from a monocular sequence. We also show how we can improve on a standard photometric warp loss by considering a warp of deep features. We show through extensive experiments that: (i) jointly training for single view depth and visual odometry improves depth prediction because of the additional constraint imposed on depths and achieves competitive results for visual odometry; (ii) deep feature-based warping loss improves upon simple photometric warp loss for both single view depth estimation and visual odometry. Our method outperforms existing learning based methods on the KITTI driving dataset in both tasks. The source code is available at https://github.com/Huangying-Zhan/Depth-VO-Feat

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to ambiguous matches at texture-less regions when performing dense reconstruction due to the aperture problem. In this work, we explore the use of learned features for the matching task in dense monocular reconstruction. We propose a novel convolutional neural network (CNN) architecture along with a deeply supervised feature learning scheme for pixel-wise regression of visual descriptors from an image which are best suited for dense monocular SLAM. In particular, our learning scheme minimizes a multi-view matching cost-volume loss with respect to the regressed features at multiple stages within the network, for explicitly learning contextual features that are suitable for dense matching between images captured by a moving monocular camera along the epipolar line. We utilize the learned features from our model for depth estimation inside a real-time dense monocular SLAM framework, where photometric error is replaced by our learned descriptor error. Our evaluation on several challenging indoor scenes demonstrate greatly improved accuracy in dense reconstructions of the well celebrated dense SLAM systems like DTAM, without compromising their real-time performance.

This paper presents an efficient framework for dense 3D scene reconstruction using input from a moving monocular camera. Visual SLAM (Simultaneous Localisation and Mapping) approaches based solely on geometric methods have proven to be quite capable of accurately tracking the pose of a moving camera and simultaneously building a map of the environment in real-time. However, most of them suffer from the 3D map being too sparse for practical use. The missing points in the generated map correspond mainly to areas lacking texture in the input images, and dense mapping systems often rely on hand-crafted priors like piecewise-planarity or piecewise-smooth depth. These priors do not always provide the required level of scene understanding to accurately fill the map. On the other hand, Convolutional Neural Networks (CNNs) have had great success in extracting high-level information from images and regressing pixel-wise surface normals, semantics, and even depth. In this work we leverage this high-level scene context learned by a deep CNN in the form of a surface normal prior. We show, in particular, that using the surface normal prior leads to better reconstructions than the weaker smoothness prior.