The success of existing deep-learning based multi-view stereo (MVS) approaches greatly depends on the availability of large-scale supervision in the form of dense depth maps. Such supervision, while not always possible, tends to hinder the generalization ability of the learned models in never-seen-before scenarios. In this paper, we propose the first unsupervised learning based MVS network, which learns the multi-view depth maps from the input multi-view images and does not need ground-truth 3D training data. Our network is symmetric in predicting depth maps for all views simultaneously, where we enforce cross-view consistency of multi-view depth maps during both training and testing stages. Thus, the learned multi-view depth maps naturally comply with the underlying 3D scene geometry. Besides, our network also learns the multi-view occlusion maps, which further improves the robustness of our network in handling real-world occlusions. Experimental results on multiple benchmarking datasets demonstrate the effectiveness of our network and the excellent generalization ability.
In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (\eg, $L_1$ or $L_2$) is often adopted as the loss function to minimize the discrepancy between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in \cite{yu2016unitbox} and \cite{rezatofighi2019generalized}. Unfortunately, all these approaches only work for axis-aligned 2D Bboxes, which cannot be applied for more general object detection task with rotated Bboxes. To resolve this issue, we investigate the IoU computation for two rotated Bboxes first and then implement a unified framework, IoU loss layer for both 2D and 3D object detection tasks. By integrating the implemented IoU loss into several state-of-the-art 3D object detectors, consistent improvements have been achieved for both bird-eye-view 2D detection and point cloud 3D detection on the public KITTI benchmark.
Stereo matching plays an indispensable part in autonomous driving, robotics and 3D scene reconstruction. We propose a novel deep learning architecture, which called CFP-Net, a Cross-Form Pyramid stereo matching network for regressing disparity from a rectified pair of stereo images. The network consists of three modules: Multi-Scale 2D local feature extraction module, Cross-form spatial pyramid module and Multi-Scale 3D Feature Matching and Fusion module. The Multi-Scale 2D local feature extraction module can extract enough multi-scale features. The Cross-form spatial pyramid module aggregates the context information in different scales and locations to form a cost volume. Moreover, it is proved to be more effective than SPP and ASPP in ill-posed regions. The Multi-Scale 3D feature matching and fusion module is proved to regularize the cost volume using two parallel 3D deconvolution structure with two different receptive fields. Our proposed method has been evaluated on the Scene Flow and KITTI datasets. It achieves state-of-the-art performance on the KITTI 2012 and 2015 benchmarks.
Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning architecture for detectingthe disparity map from a rectified pair of stereo images, called MSDC-Net. Our MSDC-Net contains two modules: multi-scale fusion 2D convolution and multi-scale residual 3D convolution modules. The multi-scale fusion 2D convolution module exploits the potential multi-scale features, which extracts and fuses the different scale features by Dense-Net. The multi-scale residual 3D convolution module learns the different scale geometry context from the cost volume which aggregated by the multi-scale fusion 2D convolution module. Experimental results on Scene Flow and KITTI datasets demonstrate that our MSDC-Net significantly outperforms other approaches in the non-occluded region.
In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps. By introducing a novel "Feedback Loop'' to connect the network input with output, LidarStereoNet could tackle both noisy Lidar points and misalignment between sensors that have been ignored in existing Lidar-stereo fusion studies. Besides, we propose to incorporate a piecewise planar model into network learning to further constrain depths to conform to the underlying 3D geometry. Extensive quantitative and qualitative evaluations on both real and synthetic datasets demonstrate the superiority of our method, which outperforms state-of-the-art stereo matching, depth completion and Lidar-Stereo fusion approaches significantly.
Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions where repetitive textures or occlusions occur. In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning. In particular, we investigate multiple ways of enforcing the epipolar constraint in flow estimation. To alleviate a ``chicken-and-egg'' type of problem encountered in dynamic scenes where multiple motions may be present, we propose a low-rank constraint as well as a union-of-subspaces constraint for training. Experimental results on various benchmarking datasets show that our method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods.
Despite deep end-to-end learning methods have shown their superiority in removing non-uniform motion blur, there still exist major challenges with the current multi-scale and scale-recurrent models: 1) Deconvolution/upsampling operations in the coarse-to-fine scheme result in expensive runtime; 2) Simply increasing the model depth with finer-scale levels cannot improve the quality of deblurring. To tackle the above problems, we present a deep hierarchical multi-patch network inspired by Spatial Pyramid Matching to deal with blurry images via a fine-to-coarse hierarchical representation. To deal with the performance saturation w.r.t. depth, we propose a stacked version of our multi-patch model. Our proposed basic multi-patch model achieves the state-of-the-art performance on the GoPro dataset while enjoying a 40x faster runtime compared to current multi-scale methods. With 30ms to process an image at 1280x720 resolution, it is the first real-time deep motion deblurring model for 720p images at 30fps. For stacked networks, significant improvements (over 1.2dB) are achieved on the GoPro dataset by increasing the network depth. Moreover, by varying the depth of the stacked model, one can adapt the performance and runtime of the same network for different application scenarios.
Recent geometric methods need reliable estimates of 3D motion parameters to procure accurate dense depth map of a complex dynamic scene from monocular images \cite{kumar2017monocular, ranftl2016dense}. Generally, to estimate \textbf{precise} measurements of relative 3D motion parameters and to validate its accuracy using image data is a challenging task. In this work, we propose an alternative approach that circumvents the 3D motion estimation requirement to obtain a dense depth map of a dynamic scene. Given per-pixel optical flow correspondences between two consecutive frames and, the sparse depth prior for the reference frame, we show that, we can effectively recover the dense depth map for the successive frames without solving for 3D motion parameters. Our method assumes a piece-wise planar model of a dynamic scene, which undergoes rigid transformation locally, and as-rigid-as-possible transformation globally between two successive frames. Under our assumption, we can avoid the explicit estimation of 3D rotation and translation to estimate scene depth. In essence, our formulation provides an unconventional way to think and recover the dense depth map of a complex dynamic scene which is incremental and motion free in nature. Our proposed method does not make object level or any other high-level prior assumption about the dynamic scene, as a result, it is applicable to a wide range of scenarios. Experimental results on the benchmarks dataset show the competence of our approach for multiple frames.
Event-based cameras can measure intensity changes (called `{\it events}') with microsecond accuracy under high-speed motion and challenging lighting conditions. With the active pixel sensor (APS), the event camera allows simultaneous output of the intensity frames. However, the output images are captured at a relatively low frame-rate and often suffer from motion blur. A blurry image can be regarded as the integral of a sequence of latent images, while the events indicate the changes between the latent images. Therefore, we are able to model the blur-generation process by associating event data to a latent image. Based on the abundant event data and the low frame-rate easily blurred images, we propose a simple and effective approach to reconstruct a high-quality and high frame-rate shape video. Starting with a single blurry frame and its event data, we propose the \textbf{Event-based Double Integral (EDI)} model. Then, we extend it to \textbf{ multiple Event-based Double Integral (mEDI)} model to get more smooth and convincing results based on multiple images and their events. We also provide an efficient solver to minimize the proposed energy model. By optimizing the energy model, we achieve significant improvements in removing general blurs and reconstructing high temporal resolution video. The video generation is based on solving a simple non-convex optimization problem in a single scalar variable. Experimental results on both synthetic and real images demonstrate the superiority of our mEDI model and optimization method in comparison to the state-of-the-art.
Recovering the absolute metric scale from a monocular camera is a challenging but highly desirable problem for monocular camera-based systems. By using different kinds of cues, various approaches have been proposed for scale estimation, such as camera height, object size etc. In this paper, firstly, we summarize different kinds of scale estimation approaches. Then, we propose a robust divide and conquer the absolute scale estimation method based on the ground plane and camera height by analyzing the advantages and disadvantages of different approaches. By using the estimated scale, an effective scale correction strategy has been proposed to reduce the scale drift during the Monocular Visual Odometry (VO) estimation process. Finally, the effectiveness and robustness of the proposed method have been verified on both public and self-collected image sequences.