In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image pair can be identified without ambiguity. However, the projected pattern significantly alters the appearance of the image. If this pattern acts as a form of adversarial noise, it could negatively impact the performance of deep learning-based methods, which are now the de-facto standard for dense stereo vision. In this paper, we propose the Active-Passive SimStereo dataset and a corresponding benchmark to evaluate the performance gap between passive and active stereo images for stereo matching algorithms. Using the proposed benchmark and an additional ablation study, we show that the feature extraction and matching modules of a selection of twenty selected deep learning-based stereo matching methods generalize to active stereo without a problem. However, the disparity refinement modules of three of the twenty architectures (ACVNet, CascadeStereo, and StereoNet) are negatively affected by the active stereo patterns due to their reliance on the appearance of the input images.
The development and application of modern technology is an essential basis for the efficient monitoring of species in natural habitats and landscapes to trace the development of ecosystems, species communities, and populations, and to analyze reasons of changes. For estimating animal abundance using methods such as camera trap distance sampling, spatial information of natural habitats in terms of 3D (three-dimensional) measurements is crucial. Additionally, 3D information improves the accuracy of animal detection using camera trapping. This study presents a novel approach to 3D camera trapping featuring highly optimized hardware and software. This approach employs stereo vision to infer 3D information of natural habitats and is designated as StereO CameRA Trap for monitoring of biodivErSity (SOCRATES). A comprehensive evaluation of SOCRATES shows not only a $3.23\%$ improvement in animal detection (bounding box $\text{mAP}_{75}$) but also its superior applicability for estimating animal abundance using camera trap distance sampling. The software and documentation of SOCRATES is provided at https://github.com/timmh/socrates
In the existing methods, LiDAR odometry shows superior performance, but visual odometry is still widely used for its price advantage. Conventionally, the task of visual odometry mainly rely on the input of continuous images. However, it is very complicated for the odometry network to learn the epipolar geometry information provided by the images. In this paper, the concept of pseudo-LiDAR is introduced into the odometry to solve this problem. The pseudo-LiDAR point cloud back-projects the depth map generated by the image into the 3D point cloud, which changes the way of image representation. Compared with the stereo images, the pseudo-LiDAR point cloud generated by the stereo matching network can get the explicit 3D coordinates. Since the 6 Degrees of Freedom (DoF) pose transformation occurs in 3D space, the 3D structure information provided by the pseudo-LiDAR point cloud is more direct than the image. Compared with sparse LiDAR, the pseudo-LiDAR has a denser point cloud. In order to make full use of the rich point cloud information provided by the pseudo-LiDAR, a projection-aware dense odometry pipeline is adopted. Most previous LiDAR-based algorithms sampled 8192 points from the point cloud as input to the odometry network. The projection-aware dense odometry pipeline takes all the pseudo-LiDAR point clouds generated from the images except for the error points as the input to the network. While making full use of the 3D geometric information in the images, the semantic information in the images is also used in the odometry task. The fusion of 2D-3D is achieved in an image-only based odometry. Experiments on the KITTI dataset prove the effectiveness of our method. To the best of our knowledge, this is the first visual odometry method using pseudo-LiDAR.
Learning accurate depth is essential to multi-view 3D object detection. Recent approaches mainly learn depth from monocular images, which confront inherent difficulties due to the ill-posed nature of monocular depth learning. Instead of using a sole monocular depth method, in this work, we propose a novel Surround-view Temporal Stereo (STS) technique that leverages the geometry correspondence between frames across time to facilitate accurate depth learning. Specifically, we regard the field of views from all cameras around the ego vehicle as a unified view, namely surroundview, and conduct temporal stereo matching on it. The resulting geometrical correspondence between different frames from STS is utilized and combined with the monocular depth to yield final depth prediction. Comprehensive experiments on nuScenes show that STS greatly boosts 3D detection ability, notably for medium and long distance objects. On BEVDepth with ResNet-50 backbone, STS improves mAP and NDS by 2.6% and 1.4%, respectively. Consistent improvements are observed when using a larger backbone and a larger image resolution, demonstrating its effectiveness
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022. For multi-view camera-only 3D detection, methods based on bird-eye-view or 3D geometric representations can leverage the stereo cues from overlapped regions between adjacent views and directly perform 3D detection without hand-crafted post-processing. However, it lacks direct semantic supervision for 2D backbones, which can be complemented by pretraining simple monocular-based detectors. Our solution is a multi-view framework for 4D detection following this paradigm. It is built upon a simple monocular detector FCOS3D++, pretrained only with object annotations of Waymo, and converts multi-view features to a 3D grid space to detect 3D objects thereon. A dual-path neck for single-frame understanding and temporal stereo matching is devised to incorporate multi-frame information. Our method finally achieves 49.75% mAPL with a single model and wins 2nd place in the WOD challenge, without any LiDAR-based depth supervision during training. The code will be released at https://github.com/Tai-Wang/Depth-from-Motion.
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection. Despite the surge, the use of the transformer for the problem of stereo matching remains relatively unexplored. In this paper, we comprehensively investigate the use of the transformer for the problem of stereo matching, especially for laparoscopic videos, and propose a new hybrid deep stereo matching framework (HybridStereoNet) that combines the best of the CNN and the transformer in a unified design. To be specific, we investigate several ways to introduce transformers to volumetric stereo matching pipelines by analyzing the loss landscape of the designs and in-domain/cross-domain accuracy. Our analysis suggests that employing transformers for feature representation learning, while using CNNs for cost aggregation will lead to faster convergence, higher accuracy and better generalization than other options. Our extensive experiments on Sceneflow, SCARED2019 and dVPN datasets demonstrate the superior performance of our HybridStereoNet.
Multi-view stereo is an important research task in computer vision while still keeping challenging. In recent years, deep learning-based methods have shown superior performance on this task. Cost volume pyramid network-based methods which progressively refine depth map in coarse-to-fine manner, have yielded promising results while consuming less memory. However, these methods fail to take fully consideration of the characteristics of the cost volumes in each stage, leading to adopt similar range search strategies for each cost volume stage. In this work, we present a novel cost volume pyramid based network with different searching strategies for multi-view stereo. By choosing different depth range sampling strategies and applying adaptive unimodal filtering, we are able to obtain more accurate depth estimation in low resolution stages and iteratively upsample depth map to arbitrary resolution. We conducted extensive experiments on both DTU and BlendedMVS datasets, and results show that our method outperforms most state-of-the-art methods.
Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural architecture search (NAS) has been applied with great success to various sparse prediction tasks, such as image classification and object detection. However, existing NAS studies on the dense prediction task, especially stereo matching, still cannot be efficiently and effectively deployed on devices of different computing capabilities. To this end, we propose to train an elastic and accurate network for stereo matching (EASNet) that supports various 3D architectural settings on devices with different computing capabilities. Given the deployment latency constraint on the target device, we can quickly extract a sub-network from the full EASNet without additional training while the accuracy of the sub-network can still be maintained. Extensive experiments show that our EASNet outperforms both state-of-the-art human-designed and NAS-based architectures on Scene Flow and MPI Sintel datasets in terms of model accuracy and inference speed. Particularly, deployed on an inference GPU, EASNet achieves a new SOTA 0.73 EPE on the Scene Flow dataset with 100 ms, which is 4.5$\times$ faster than LEAStereo with a better quality model.
We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which introduces diffusion models, a type of powerful generative models, into the iterative stereo matching network. To this end, we design a new diffusion kernel and additional stereo constraints to facilitate stereo matching and depth estimation in the network. We further present a multi-level stereo network architecture to handle high-resolution (up to 4k) inputs without requiring unaffordable memory footprint. Given a set of sparse-view color images of a human, the proposed multi-level diffusion-based stereo network can produce highly accurate depth maps, which are then converted into a high-quality 3D human model through an efficient multi-view fusion strategy. Overall, our method enables automatic reconstruction of human models with quality on par to high-end dense-view camera rigs, and this is achieved using a much more light-weight hardware setup. Experiments show that our method outperforms state-of-the-art methods by a large margin both qualitatively and quantitatively.
Depth estimation is one of the key technologies in some fields such as autonomous driving and robot navigation. However, the traditional method of using a single sensor is inevitably limited by the performance of the sensor. Therefore, a precision and robust method for fusing the LiDAR and stereo cameras is proposed. This method fully combines the advantages of the LiDAR and stereo camera, which can retain the advantages of the high precision of the LiDAR and the high resolution of images respectively. Compared with the traditional stereo matching method, the texture of the object and lighting conditions have less influence on the algorithm. Firstly, the depth of the LiDAR data is converted to the disparity of the stereo camera. Because the density of the LiDAR data is relatively sparse on the y-axis, the converted disparity map is up-sampled using the interpolation method. Secondly, in order to make full use of the precise disparity map, the disparity map and stereo matching are fused to propagate the accurate disparity. Finally, the disparity map is converted to the depth map. Moreover, the converted disparity map can also increase the speed of the algorithm. We evaluate the proposed pipeline on the KITTI benchmark. The experiment demonstrates that our algorithm has higher accuracy than several classic methods.
The proposal of Pseudo-Lidar representation has significantly narrowed the gap between visual-based and active Lidar-based 3D object detection. However, current researches exclusively focus on pushing the accuracy improvement of Pseudo-Lidar by taking the advantage of complex and time-consuming neural networks. Seldom explore the profound characteristics of Pseudo-Lidar representation to obtain the promoting opportunities. In this paper, we dive deep into the pseudo Lidar representation and argue that the performance of 3D object detection is not fully dependent on the high precision stereo depth estimation. We demonstrate that even for the unreliable depth estimation, with proper data processing and refining, it can achieve comparable 3D object detection accuracy. With this finding, we further show the possibility that utilizing fast but inaccurate stereo matching algorithms in the Pseudo-Lidar system to achieve low latency responsiveness. In the experiments, we develop a system with a less powerful stereo matching predictor and adopt the proposed refinement schemes to improve the accuracy. The evaluation on the KITTI benchmark shows that the presented system achieves competitive accuracy to the state-of-the-art approaches with only 23 ms computing, showing it is a suitable candidate for deploying to real car-hold applications.
Display technologies have evolved over the years. It is critical to develop practical HDR capturing, processing, and display solutions to bring 3D technologies to the next level. Depth estimation of multi-exposure stereo image sequences is an essential task in the development of cost-effective 3D HDR video content. In this paper, we develop a novel deep architecture for multi-exposure stereo depth estimation. The proposed architecture has two novel components. First, the stereo matching technique used in traditional stereo depth estimation is revamped. For the stereo depth estimation component of our architecture, a mono-to-stereo transfer learning approach is deployed. The proposed formulation circumvents the cost volume construction requirement, which is replaced by a ResNet based dual-encoder single-decoder CNN with different weights for feature fusion. EfficientNet based blocks are used to learn the disparity. Secondly, we combine disparity maps obtained from the stereo images at different exposure levels using a robust disparity feature fusion approach. The disparity maps obtained at different exposures are merged using weight maps calculated for different quality measures. The final predicted disparity map obtained is more robust and retains best features that preserve the depth discontinuities. The proposed CNN offers flexibility to train using standard dynamic range stereo data or with multi-exposure low dynamic range stereo sequences. In terms of performance, the proposed model surpasses state-of-the-art monocular and stereo depth estimation methods, both quantitatively and qualitatively, on challenging Scene flow and differently exposed Middlebury stereo datasets. The architecture performs exceedingly well on complex natural scenes, demonstrating its usefulness for diverse 3D HDR applications.
We address the problem of registering synchronized color (RGB) and multi-spectral (MS) images featuring very different resolution by solving stereo matching correspondences. Purposely, we introduce a novel RGB-MS dataset framing 13 different scenes in indoor environments and providing a total of 34 image pairs annotated with semi-dense, high-resolution ground-truth labels in the form of disparity maps. To tackle the task, we propose a deep learning architecture trained in a self-supervised manner by exploiting a further RGB camera, required only during training data acquisition. In this setup, we can conveniently learn cross-modal matching in the absence of ground-truth labels by distilling knowledge from an easier RGB-RGB matching task based on a collection of about 11K unlabeled image triplets. Experiments show that the proposed pipeline sets a good performance bar (1.16 pixels average registration error) for future research on this novel, challenging task.
Stereo matching of high-resolution satellite images (HRSI) is still a fundamental but challenging task in the field of photogrammetry and remote sensing. Recently, deep learning (DL) methods, especially convolutional neural networks (CNNs), have demonstrated tremendous potential for stereo matching on public benchmark datasets. However, datasets for stereo matching of satellite images are scarce. To facilitate further research, this paper creates and publishes a challenging dataset, termed WHU-Stereo, for stereo matching DL network training and testing. This dataset is created by using airborne LiDAR point clouds and high-resolution stereo imageries taken from the Chinese GaoFen-7 satellite (GF-7). The WHU-Stereo dataset contains more than 1700 epipolar rectified image pairs, which cover six areas in China and includes various kinds of landscapes. We have assessed the accuracy of ground-truth disparity maps, and it is proved that our dataset achieves comparable precision compared with existing state-of-the-art stereo matching datasets. To verify its feasibility, in experiments, the hand-crafted SGM stereo matching algorithm and recent deep learning networks have been tested on the WHU-Stereo dataset. Experimental results show that deep learning networks can be well trained and achieves higher performance than hand-crafted SGM algorithm, and the dataset has great potential in remote sensing application. The WHU-Stereo dataset can serve as a challenging benchmark for stereo matching of high-resolution satellite images, and performance evaluation of deep learning models. Our dataset is available at https://github.com/Sheng029/WHU-Stereo
This work proposes an end-to-end approach to estimate full 3D hand pose from stereo cameras. Most existing methods of estimating hand pose from stereo cameras apply stereo matching to obtain depth map and use depth-based solution to estimate hand pose. In contrast, we propose to bypass the stereo matching and directly estimate the 3D hand pose from the stereo image pairs. The proposed neural network architecture extends from any keypoint predictor to estimate the sparse disparity of the hand joints. In order to effectively train the model, we propose a large scale synthetic dataset that is composed of stereo image pairs and ground truth 3D hand pose annotations. Experiments show that the proposed approach outperforms the existing methods based on the stereo depth.
Deep learning (DL) methods are widely investigated for stereo image matching tasks due to their reported high accuracies. However, their transferability/generalization capabilities are limited by the instances seen in the training data. With satellite images covering large-scale areas with variances in locations, content, land covers, and spatial patterns, we expect their performances to be impacted. Increasing the number and diversity of training data is always an option, but with the ground-truth disparity being limited in remote sensing due to its high cost, it is almost impossible to obtain the ground-truth for all locations. Knowing that classical stereo matching methods such as Census-based semi-global-matching (SGM) are widely adopted to process different types of stereo data, we therefore, propose a finetuning method that takes advantage of disparity maps derived from SGM on target stereo data. Our proposed method adopts a simple scheme that uses the energy map derived from the SGM algorithm to select high confidence disparity measurements, at the same utilizing the images to limit these selected disparity measurements on texture-rich regions. Our approach aims to investigate the possibility of improving the transferability of current DL methods to unseen target data without having their ground truth as a requirement. To perform a comprehensive study, we select 20 study-sites around the world to cover a variety of complexities and densities. We choose well-established DL methods like geometric and context network (GCNet), pyramid stereo matching network (PSMNet), and LEAStereo for evaluation. Our results indicate an improvement in the transferability of the DL methods across different regions visually and numerically.
In stereoscope-based Minimally Invasive Surgeries (MIS), dense stereo matching plays an indispensable role in 3D shape recovery, AR, VR, and navigation tasks. Although numerous Deep Neural Network (DNN) approaches are proposed, the conventional prior-free approaches are still popular in the industry because of the lack of open-source annotated data set and the limitation of the task-specific pre-trained DNNs. Among the prior-free stereo matching algorithms, there is no successful real-time algorithm in none GPU environment for MIS. This paper proposes the first CPU-level real-time prior-free stereo matching algorithm for general MIS tasks. We achieve an average 17 Hz on 640*480 images with a single-core CPU (i5-9400) for surgical images. Meanwhile, it achieves slightly better accuracy than the popular ELAS. The patch-based fast disparity searching algorithm is adopted for the rectified stereo images. A coarse-to-fine Bayesian probability and a spatial Gaussian mixed model were proposed to evaluate the patch probability at different scales. An optional probability density function estimation algorithm was adopted to quantify the prediction variance. Extensive experiments demonstrated the proposed method's capability to handle ambiguities introduced by the textureless surfaces and the photometric inconsistency from the non-Lambertian reflectance and dark illumination. The estimated probability managed to balance the confidences of the patches for stereo images at different scales. It has similar or higher accuracy and fewer outliers than the baseline ELAS in MIS, while it is 4-5 times faster. The code and the synthetic data sets are available at https://github.com/JingweiSong/BDIS-v2.
Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two mainstream methods. However, the former usually suffers from overfitting while building cost volume, and the latter has a limited generalization due to the lack of geometric constraint. To solve these problems, we propose a novel multimodal neural network, namely UAMD-Net, for dense depth completion based on fusion of binocular stereo matching and the weak constrain from the sparse point clouds. Specifically, the sparse point clouds are converted to sparse depth map and sent to the multimodal feature encoder (MFE) with binocular image, constructing a cross-modal cost volume. Then, it will be further processed by the multimodal feature aggregator (MFA) and the depth regression layer. Furthermore, the existing multimodal methods ignore the problem of modal dependence, that is, the network will not work when a certain modal input has a problem. Therefore, we propose a new training strategy called Modal-dropout which enables the network to be adaptively trained with multiple modal inputs and inference with specific modal inputs. Benefiting from the flexible network structure and adaptive training method, our proposed network can realize unified training under various modal input conditions. Comprehensive experiments conducted on KITTI depth completion benchmark demonstrate that our method produces robust results and outperforms other state-of-the-art methods.
Stereo matching is an essential basis for various applications, but most stereo matching methods have poor generalization performance and require a fixed disparity search range. Moreover, current stereo matching methods focus on the scenes that only have positive disparities, but ignore the scenes that contain both positive and negative disparities, such as 3D movies. In this paper, we present a new stereo matching pipeline that first computes semi-dense disparity maps based on binocular disparity, and then completes the rest depending on monocular cues. The new stereo matching pipeline have the following advantages: It 1) has better generalization performance than most of the current stereo matching methods; 2) relaxes the limitation of a fixed disparity search range; 3) can handle the scenes that involve both positive and negative disparities, which has more potential applications, such as view synthesis in 3D multimedia and VR/AR. Experimental results demonstrate the effectiveness of our new stereo matching pipeline.
In this paper, we study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. Due to the difficulty of obtaining ground-truth disparity labels in diverse real-world systems, we start from an unsupervised learning perspective. However, resolution asymmetry caused by unknown degradations between two views hinders the effectiveness of the generally assumed photometric consistency. To overcome this challenge, we propose to impose the consistency between two views in a feature space instead of the image space, named feature-metric consistency. Interestingly, we find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features. These features can then be utilized to formulate a feature-metric loss to avoid the photometric inconsistency. Moreover, we introduce a self-boosting strategy to optimize the feature extractor progressively, which further strengthens the feature-metric consistency. Experiments on both simulated datasets with various degradations and a self-collected real-world dataset validate the superior performance of the proposed method over existing solutions.