Over the past few years, there has been remarkable progress in research on 3D point clouds and their use in autonomous driving scenarios has become widespread. However, deep learning methods heavily rely on annotated data and often face domain generalization issues. Unlike 2D images whose domains usually pertain to the texture information present in them, the features derived from a 3D point cloud are affected by the distribution of the points. The lack of a 3D domain adaptation benchmark leads to the common practice of training a model on one benchmark (e.g. Waymo) and then assessing it on another dataset (e.g. KITTI). This setting results in two distinct domain gaps: scenarios and sensors, making it difficult to analyze and evaluate the method accurately. To tackle this problem, this paper presents ${\color{Red}\text{LiDAR}}$ Dataset with ${\color{Red}\text{C}}{\text{ross}} - {\color{Red}\text{S}}{\text{ensors}}$ (LiDAR-CS Dataset), which contains large-scale annotated LiDAR point cloud under six groups of different sensors but with the same corresponding scenarios, captured from hybrid realistic LiDAR simulator. To our knowledge, LiDAR-CS Dataset is the first dataset that addresses the sensor-related gaps in the domain of 3D object detection in real traffic. Furthermore, we evaluate and analyze the performance using various baseline detectors and demonstrated its potential applications. Project page: https://opendriving.github.io/lidar-cs.

Due to the domain differences and unbalanced disparity distribution across multiple datasets, current stereo matching approaches are commonly limited to a specific dataset and generalize poorly to others. Such domain shift issue is usually addressed by substantial adaptation on costly target-domain ground-truth data, which cannot be easily obtained in practical settings. In this paper, we propose to dig into uncertainty estimation for robust stereo matching. Specifically, to balance the disparity distribution, we employ a pixel-level uncertainty estimation to adaptively adjust the next stage disparity searching space, in this way driving the network progressively prune out the space of unlikely correspondences. Then, to solve the limited ground truth data, an uncertainty-based pseudo-label is proposed to adapt the pre-trained model to the new domain, where pixel-level and area-level uncertainty estimation are proposed to filter out the high-uncertainty pixels of predicted disparity maps and generate sparse while reliable pseudo-labels to align the domain gap. Experimentally, our method shows strong cross-domain, adapt, and joint generalization and obtains 1st place on the stereo task of Robust Vision Challenge 2020. Additionally, our uncertainty-based pseudo-labels can be extended to train monocular depth estimation networks in an unsupervised way and even achieves comparable performance with the supervised methods.

Single image-based dehazing has achieved remarkable progress with the development of deep learning technologies. End-to-end neural networks have been proposed to learn a direct hazy-to-clear image translation to recover the clear structures and edges cues from the hazy inputs. However, the frequency domain information is explored insufficiently and lots of intermediate structure and texture related cues of current dehazing networks are ignored, which limits the performances of current approaches. To handle these limitations mentioned above, a wavelet spatial attention based multi-stream feedback network (WSAMF-Net) is proposed for effective single image dehazing. Specifically, the proposed wavelet spatial attention utilizes both frequency-domain and spatial-domain information to enhance the extracted features for better structures and edges. Meanwhile, an enhanced multi-stream based cross feature fusion strategy, including vertical and horizontal attentions, is proposed to reweight and fuse the intermediate features of each stream to acquire more meaningful aggregated features, while the weight sharing strategy is used to achieve a good trade-off between performance and parameters. Besides, feedback mechanism is also designed to provide strong reconstruction ability. Furthermore, we propose a critical real-world industrial dataset (IDS) with images captured in real-world industrial quarry scenarios for research uses. Extensive experiments on various benchmarking datasets, including both synthetic and real-world datasets, demonstrate the superiority of our WSAMF-Net over state-of-the-art single image dehazing methods. The IDS dataset will be available athttps://github.com/XBSong/IDS-Datasethttps://github.com/XBSong/IDS-Dataset.

Single image dehazing is a challenging and ill-posed problem due to severe information degeneration of images captured in hazy conditions. Remarkable progresses have been achieved by deep-learning based image dehazing methods, where residual learning is commonly used to separate the hazy image into clear and haze components. However, the nature of low similarity between haze and clear components is commonly neglected, while the lack of constraint of contrastive peculiarity between the two components always restricts the performance of these approaches. To deal with these problems, we propose an end-to-end self-regularized network (TUSR-Net) which exploits the contrastive peculiarity of different components of the hazy image, i.e, self-regularization (SR). In specific, the hazy image is separated into clear and hazy components and constraint between different image components, i.e., self-regularization, is leveraged to pull the recovered clear image closer to groundtruth, which largely promotes the performance of image dehazing. Meanwhile, an effective triple unfolding framework combined with dual feature to pixel attention is proposed to intensify and fuse the intermediate information in feature, channel and pixel levels, respectively, thus features with better representational ability can be obtained. Our TUSR-Net achieves better trade-off between performance and parameter size with weight-sharing strategy and is much more flexible. Experiments on various benchmarking datasets demonstrate the superiority of our TUSR-Net over state-of-the-art single image dehazing methods.

Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major challenge because existing hard assignment methods cannot deal with outliers naturally. Alternatively, the soft matching-based methods have been proposed to learn the matching probability rather than hard assignment. However, in this paper, we prove that these methods have an inherent ambiguity causing many deceptive correspondences. To address the above challenges, we propose to learn a partial permutation matching matrix, which does not assign corresponding points to outliers, and implements hard assignment to prevent ambiguity. However, this proposal poses two new problems, i.e. existing hard assignment algorithms can only solve a full rank permutation matrix rather than a partial permutation matrix, and this desired matrix is defined in the discrete space, which is non-differentiable. In response, we design a dedicated soft-to-hard (S2H) matching procedure within the registration pipeline consisting of two steps: solving the soft matching matrix (S-step) and projecting this soft matrix to the partial permutation matrix (H-step). Specifically, we augment the profit matrix before the hard assignment to solve an augmented permutation matrix, which is cropped to achieve the final partial permutation matrix. Moreover, to guarantee end-to-end learning, we supervise the learned partial permutation matrix but propagate the gradient to the soft matrix instead. Our S2H matching procedure can be easily integrated with existing registration frameworks, which has been verified in representative frameworks including DCP, RPMNet, and DGR. Extensive experiments have validated our method, which creates a new state-of-the-art performance.

3-D point cloud registration in remote sensing field has been greatly advanced by deep learning-based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondence-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this letter, we propose a correspondence-free unsupervised point cloud registration (UPCR) method from the representation separation perspective. First, we model the input point cloud as a combination of pose-invariant representation and pose-related representation. Second, the pose-related representation is used to learn the relative pose w.r.t. a “latent canonical shape” for thesourceandtargetpoint clouds, respectively. Third, the rigid transformation is obtained from the above two learned relative poses. Our method not only filters out the disturbance in pose-invariant representation but also is robust to partial-to-partial point clouds or noise. Experiments on benchmark datasets demonstrate that our unsupervised method achieves comparable if not better performance than state-of-the-art supervised registration methods.The source code will be made public.

Camera sensors have been widely used in Driver-Assistance and Autonomous Driving Systems due to their rich texture information. Recently, with the development of deep learning techniques, many approaches have been proposed to detect objects in 3D from a single frame, however, there is still much room for improvement. In this paper, we generally review the recently proposed state-of-the-art monocular-based 3D object detection approaches first. Based on the analysis of the disadvantage of previous center-based frameworks, a novel feature aggregation strategy has been proposed to boost the 3D object detection by exploring the context information. Specifically, an Instance-Guided Spatial Attention (IGSA) module is proposed to collect the local instance information and the Channel-Wise Feature Attention (CWFA) module is employed for aggregating the global context information. In addition, an instance-guided object regression strategy is also proposed to alleviate the influence of center location prediction uncertainty in the inference process. Finally, the proposed approach has been verified on the public 3D object detection benchmark. The experimental results show that the proposed approach can significantly boost the performance of the baseline method on both 3D detection and 2D Bird’s-Eye View among all three categories. Furthermore, our method outperforms all the monocular-based methods (even these trained with depth as auxiliary inputs) and achieves state-of-the-art performance on the KITTI benchmark.

Despite the remarkable progresses achieved in depth map super-resolution (DSR), it remains a major challenge to tackle with real-world degradation of low-resolution (LR) depth maps. Synthetic datasets are mainly used in existing DSR approaches, which is quite different from what would get from a real depth sensor. Besides, the enhancements of features in existing DSR approaches are not sufficiently enough, which also limit the performance. To alleviate these problems, we first propose two types of degradation models to describe the generation of LR depth maps, including bi-cubic down-sampling with noise and interval down-sampling, and different DSR models are learned correspondingly. Then, we propose a weighted attention fusion strategy that is embedded into a progressive residual learning framework, which guarantees that the high-resolution (HR) depth maps can be well recovered in a coarse-to-fine manner. The weighted attention fusion strategy can enhance the features with abundant high-frequency components in both global and local manners, thus better HR depth maps can be expected. Besides, to re-use the effective information in the progressive process sufficiently, a multi-stage fusion module is combined into the proposed framework, and the Total Generalized Variation (TGV) regularization and input loss are exploited to further improve the performance of our method. Extensive experiments of different benchmarks demonstrate the superiority of our approach over the state-of-the-art (SOTA) approaches.

Annotating the LiDAR point cloud is crucial for deep learning-based 3D object detection tasks. Due to expensive labeling costs, data augmentation has been taken as a necessary module and plays an important role in training the neural network. "Copy" and "paste" (i.e., GT-Aug) is the most commonly used data augmentation strategy, however, the occlusion between objects has not been taken into consideration. To handle the above limitation, we propose a rendering-based LiDAR augmentation frame-work (i.e., LiDAR-Aug) to enrich the training data and boost the performance of LiDAR-based 3D object detectors. The proposed LiDAR-Aug is a plug-and-play module that can be easily integrated into different types of 3D object detection frameworks. Compared to the traditional object augmentation methods, LiDAR-Aug is more realistic and effective. Finally, we verify the proposed framework on the public KITTI dataset with different 3D object detectors. The experimental results show the superiority of our method compared to other data augmentation strategies. We plan to make our data and code public to help other researchers reproduce our results.

Existing deep learning-based approaches for monocular 3D object detection in autonomous driving often model the object as a rotated 3D cuboid while the object’s geometric shape has been ignored. In this work, we propose an approach for incorporating the shape-aware 2D/3D constraints into the 3D detection framework. Specifically, we employ the deep neural network to learn distinguished 2D keypoints in the 2D image domain and regress their corresponding 3D coordinates in the local 3D object coordinate first. Then the 2D/3D geometric constraints are built by these correspondences for each object to boost the detection performance. For generating the ground truth of 2D/3D keypoints, an automatic model-fitting approach has been proposed by fitting the deformed 3D object model and the object mask in the 2D image. The proposed framework has been verified on the public KITTI dataset and the experimental results demonstrate that by using additional geometrical constraints the detection performance has been significantly improved as compared to the baseline method. More importantly, the proposed framework achieves state-of-the-art performance with real time. Data and code will be available at https://github.com/zongdai/AutoShape

3D object detection is a key perception component in autonomous driving. Most recent approaches are based on LiDAR sensors only or fused with cameras. Maps (e.g., High Definition Maps), a basic infrastructure for intelligent vehicles, however, have not been well exploited for boosting object detection tasks. In this paper, we propose a simple but effective framework - MapFusion to integrate the map information into modern 3D object detector pipelines. In particular, we design a FeatureAgg module for HD Map feature extraction and fusion, and a MapSeg module as an auxiliary segmentation head for the detection backbone. Our proposed MapFusion is detector independent and can be easily integrated into different detectors. The experimental results of three different baselines on large public autonomous driving dataset demonstrate the superiority of the proposed framework. By fusing the map information, we can achieve 1.27 to 2.79 points improvements for mean Average Precision (mAP) on three strong 3D object detection baselines.

The success of supervised learning-based single image depth estimation methods critically depends on the availability of large-scale dense per-pixel depth annotations, which requires both laborious and expensive annotation process. Therefore, the self-supervised methods are much desirable, which attract significant attention recently. However, depth maps predicted by existing self-supervised methods tend to be blurry with many depth details lost. To overcome these limitations, we propose a novel framework, named MLDA-Net, to obtain per-pixel depth maps with shaper boundaries and richer depth details. Our first innovation is a multi-level feature extraction (MLFE) strategy which can learn rich hierarchical representation. Then, a dual-attention strategy, combining global attention and structure attention, is proposed to intensify the obtained features both globally and locally, resulting in improved depth maps with sharper boundaries. Finally, a reweighted loss strategy based on multi-level outputs is proposed to conduct effective supervision for self-supervised depth estimation. Experimental results demonstrate that our MLDA-Net framework achieves state-of-the-art depth prediction results on the KITTI benchmark for self-supervised monocular depth estimation with different input modes and training modes. Extensive experiments on other benchmark datasets further confirm the superiority of our proposed approach.

Recently, significant progress has been achieved in analyzing the 3D point cloud with deep learning techniques. However, existing networks suffer from poor generalization and robustness to arbitrary rotations applied to the input point cloud. Different from traditional strategies that improve the rotation robustness with data augmentation or specifically designed spherical representation or harmonics-based kernels, we propose to rotate the point cloud into a canonical viewpoint for boosting the following downstream target task, e.g., object classification and part segmentation. Specifically, the canonical viewpoint is predicted by the network RotPredictor in an unsupervised way and the loss function is only built on the target task. Our RotPredictor satisfies the rotation equivariance property in (3) approximately and the predication output has the linear relationship with the applied rotation transformation. In addition, the RotPredictor is an independent plug and play module, which can be employed by any point-based deep learning framework without extra burden. Experimental results on the public model classification dataset ModelNet40 show the performance for all baselines can be boosted by integrating the proposed module. In addition, by adding our proposed module, we can achieve the state-of-the-art classification accuracy with 90.2% on the rotation-augmented ModelNet40 benchmark.

Despite the remarkable progresses made in deep learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge. Existing DSR model is generally trained and tested on synthetic dataset, which is very different from what would get from a real depth sensor. In this paper, we argue that DSR models trained under this setting are restrictive and not effective in dealing with realworld DSR tasks. We make two contributions in tackling real-world degradation of different depth sensors. First, we propose to classify the generation of LR depth maps into two types: non-linear downsampling with noise and interval downsampling, for which DSR models are learned correspondingly. Second, we propose a new framework for real-world DSR, which consists of four modules : 1) An iterative residual learning module with deep supervision to learn effective high-frequency components of depth maps in a coarse-to-fine manner; 2) A channel attention strategy to enhance channels with abundant high-frequency components; 3) A multi-stage fusion module to effectively reexploit the results in the coarse-to-fine process; and 4) A depth refinement module to improve the depth map by TGV regularization and input loss. Extensive experiments on benchmarking datasets demonstrate the superiority of our method over current state-of-the-art DSR methods.

Existing LiDAR-based 3D object detectors usually focus on the single-frame detection, while ignoring the spatiotemporal information in consecutive point cloud frames. In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences. The proposed model comprises a spatial feature encoding component and a spatiotemporal feature aggregation component. In the former component, a novel Pillar Message Passing Network (PMPNet) is proposed to encode each discrete point cloud frame. It adaptively collects information for a pillar node from its neighbors by iterative message passing, which effectively enlarges the receptive field of the pillar feature. In the latter component, we propose an Attentive Spatiotemporal Transformer GRU (AST-GRU) to aggregate the spatiotemporal information, which enhances the conventional ConvGRU with an attentive memory gating mechanism. AST-GRU contains a Spatial Transformer Attention (STA) module and a Temporal Transformer Attention (TTA) module, which can emphasize the foreground objects and align the dynamic objects, respectively. Experimental results demonstrate that the proposed 3D video object detector achieves state-of-the-art performance on the large-scale nuScenes benchmark.

Currently, in Autonomous Driving (AD), most of the 3D object detection frameworks (either anchor- or anchor-free-based) consider the detection as a Bounding Box (BBox) regression problem. However, this compact representation is not sufficient to explore all the information of the objects. To tackle this problem, we propose a simple but practical detection framework to jointly predict the 3D BBox and instance segmentation. For instance segmentation, we propose a Spatial Embeddings (SEs) strategy to assemble all foreground points into their corresponding object centers. Base on the SE results, the object proposals can be generated based on a simple clustering strategy. For each cluster, only one proposal is generated. Therefore, the Non-Maximum Suppression (NMS) process is no longer needed here. Finally, with our proposed instance-aware ROI pooling, the BBox is refined by a second-stage network. Experimental results on the public KITTI dataset show that the proposed SEs can significantly improve the instance segmentation results compared with other feature embedding-based method. Meanwhile, it also outperforms most of the 3D object detectors on the KITTI testing benchmark.

Autonomous driving has attracted tremendous attention especially in the past few years. The key techniques for a self-driving car include solving tasks like 3D map construction, self-localization, parsing the driving road and understanding objects, which enable vehicles to reason and act. However, large scale data set for training and system evaluation is still a bottleneck for developing robust perception models. In this paper, we present the ApolloScape dataset [1] and its applications for autonomous driving. Compared with existing public datasets from real scenes, e.g., KITTI [2] or Cityscapes [3] , ApolloScape contains much large and richer labelling including holistic semantic dense point cloud for each site, stereo, per-pixel semantic labelling, lanemark labelling, instance segmentation, 3D car instance, high accurate location for every frame in various driving videos from multiple sites, cities and daytimes. For each task, it contains at lease 15x larger amount of images than SOTA datasets. To label such a complete dataset, we develop various tools and algorithms specified for each task to accelerate the labelling process, such as joint 3D-2D segment labeling, active labelling in videos etc. Depend on ApolloScape, we are able to develop algorithms jointly consider the learning and inference of multiple tasks. In this paper, we provide a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving. We show that practically, sensor fusion and joint learning of multiple tasks are beneficial to achieve a more robust and accurate system. We expect our dataset and proposed relevant algorithms can support and motivate researchers for further development of multi-sensor fusion and multi-task learning in the field of computer vision.

Recovering an 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 and object size. In this paper, first, we summarize different kinds of scale estimation approaches. Then, we propose a robust divide-and-conquer 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 estimation process. Finally, the effectiveness and robustness of the proposed method have been verified on both public and self-collected image sequences.

In the 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 (e.g, 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 [1] and [2]. Unfortunately, all these approaches only work for axis-aligned 2D Boxes, which cannot be applied for more general object detection task with rotated Boxes. To resolve this issue, we investigate the IoU computation for two rotated Boxes 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 [3] benchmark.

Autonomous driving has attracted remarkable attention from both industry and academia. An important task is to estimate 3D properties (e.g. translation, rotation and shape) of a moving or parked vehicle on the road. This task, while critical, is still under-researched in the computer vision community – partially owing to the lack of large scale and fully-annotated 3D car database suitable for autonomous driving research. In this paper, we contribute the first large scale database suitable for 3D car instance understanding – ApolloCar3D. The dataset contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20× larger than PASCAL3D+ and KITTI, the current state-of-the-art. To enable efficient labelling in 3D, we build a pipeline by considering 2D-3D keypoint correspondences for a single instance and 3D relationship among multiple instances. Equipped with such dataset, we build various baseline algorithms with the state-of-the-art deep convolutional neural networks. Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints. We show that using keypoints significantly improves fitting performance. Finally, we develop a new 3D metric jointly considering 3D pose and 3D shape, allowing for comprehensive evaluation and ablation study.

It is of practical interest to automatically calibrate the multiple sensors in autonomous vehicles. In this paper, we deal with an interesting case when used low-resolution Lidar and present a practical approach to extrinsic calibration between monocular camera and Lidar with sparse 3D measurements. We formulate the problem as directly minimizing the feature error evaluated between frames following the way of image warping. To overcome the difficulties in the optimization problem, we propose to use the distance transform and further projection error model to obtain the key approximated edge points that are sensitive to the loss function. Finally, the loss minimization is solved by an efficient random selection algorithm. Experimental results on KITTI dataset show that our proposed method can achieve competitive results and an improvement in translation estimation particularly.

Recovering absolute scale (i.e. metric information) from monocular vision system is a very challenging problem yet is highly desirable for vision-based autonomous driving. This paper proposes a new method for scale recovery, based on the idea of knowing camera height (relative to ground-plane). While this idea of using known camera height is not new in this context, existing implementations of this idea suffer significantly from severe numerical instability arisen in the ground plane homography decomposition stage. Our novel contribution of this work is to alleviate this issue by a divide and conquer approach, i.e. decomposing the motion parameters in the homography from the structure parameters of the ground plane. We also describe a robust procedure to correct scale drift in the monocular visual odometry system. Experimental results on KITTI standard benchmark dataset [1] and our self-collected driving dataset both show significant improvements.

Supervised classification algorithms such as Boosting and SVM have achieved significant success in the field of computer vision for classification and object recognition. However, the performance of the classifier decreases rapidly if there are insufficient labeled training samples. In this paper, a semi-supervised boosting algorithm is proposed to overcome this limitation. First, a few labeled instances are use to estimate probabilistic class labels for unlabeled samples using Gaussian Mixture Models after a dimension reduction step performed via Principal Component Analysis. Then, we apply a boosting strategy on decision stumps trained using the soft labeled instances thus obtained. The performances of our strategy are evaluated on several state-of-the-art classification datasets, as well as on a pedestrian detection and recognition problem. Experimental results demonstrate the interest of taking into account additional data in the training process.

In this paper, we propose an effective approach for moving object detection based on modeling the ego-motion uncertainty and using a graph-cut based motion segmentation. First, the relative camera pose is estimated by minimizing the sum of reprojection errors and its covariance matrix is calculated using a first-order errors propagation method. Next, a motion likelihood for each pixel is obtained by propagating the uncertainty of the ego-motion to the Residual Image Motion Flow (RIMF). Finally, the motion likelihood and the depth gradient are used in a graph-cut based approach as region and boundary terms respectively, in order to obtain the moving objects segmentation. Experimental results on real-world data show that our approach can detect dynamic objects which move on the epipolar plane or that are partially occluded in complex urban traffic scenes.