Depth estimation is crucial for intelligent systems, enabling applications from autonomous navigation to augmented reality. While traditional stereo and active depth sensors have limitations in cost, power, and robustness, dual-pixel (DP) technology, ubiquitous in modern cameras, offers a compelling alternative. This paper introduces DiFuse-Net, a novel modality decoupled network design for disentangled RGB and DP based depth estimation. DiFuse-Net features a window bi-directional parallax attention mechanism (WBiPAM) specifically designed to capture the subtle DP disparity cues unique to smartphone cameras with small aperture. A separate encoder extracts contextual information from the RGB image, and these features are fused to enhance depth prediction. We also propose a Cross-modal Transfer Learning (CmTL) mechanism to utilize large-scale RGB-D datasets in the literature to cope with the limitations of obtaining large-scale RGB-DP-D dataset. Our evaluation and comparison of the proposed method demonstrates its superiority over the DP and stereo-based baseline methods. Additionally, we contribute a new, high-quality, real-world RGB-DP-D training dataset, named Dual-Camera Dual-Pixel (DCDP) dataset, created using our novel symmetric stereo camera hardware setup, stereo calibration and rectification protocol, and AI stereo disparity estimation method.
Event cameras have the potential to revolutionize the field of robot vision, particularly in areas like stereo disparity estimation, owing to their high temporal resolution and high dynamic range. Many studies use deep learning for event camera stereo disparity estimation. However, these methods fail to fully exploit the temporal information in the event stream to acquire clear event representations. Additionally, there is room for further reduction in pixel shifts in the feature maps before constructing the cost volume. In this paper, we propose EV-MGDispNet, a novel event-based stereo disparity estimation method. Firstly, we propose an edge-aware aggregation (EAA) module, which fuses event frames and motion confidence maps to generate a novel clear event representation. Then, we propose a motion-guided attention (MGA) module, where motion confidence maps utilize deformable transformer encoders to enhance the feature map with more accurate edges. Finally, we also add a census left-right consistency loss function to enhance the left-right consistency of stereo event representation. Through conducting experiments within challenging real-world driving scenarios, we validate that our method outperforms currently known state-of-the-art methods in terms of mean absolute error (MAE) and root mean square error (RMSE) metrics.
Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.
Stereo matching is a core task for many computer vision and robotics applications. Despite their dominance in traditional stereo methods, the hand-crafted Markov Random Field (MRF) models lack sufficient modeling accuracy compared to end-to-end deep models. While deep learning representations have greatly improved the unary terms of the MRF models, the overall accuracy is still severely limited by the hand-crafted pairwise terms and message passing. To address these issues, we propose a neural MRF model, where both potential functions and message passing are designed using data-driven neural networks. Our fully data-driven model is built on the foundation of variational inference theory, to prevent convergence issues and retain stereo MRF's graph inductive bias. To make the inference tractable and scale well to high-resolution images, we also propose a Disparity Proposal Network (DPN) to adaptively prune the search space of disparity. The proposed approach ranks $1^{st}$ on both KITTI 2012 and 2015 leaderboards among all published methods while running faster than 100 ms. This approach significantly outperforms prior global methods, e.g., lowering D1 metric by more than 50% on KITTI 2015. In addition, our method exhibits strong cross-domain generalization and can recover sharp edges. The codes at https://github.com/aeolusguan/NMRF
Dense matching is crucial for 3D scene reconstruction since it enables the recovery of scene 3D geometry from image acquisition. Deep Learning (DL)-based methods have shown effectiveness in the special case of epipolar stereo disparity estimation in the computer vision community. DL-based methods depend heavily on the quality and quantity of training datasets. However, generating ground-truth disparity maps for real scenes remains a challenging task in the photogrammetry community. To address this challenge, we propose a method for generating ground-truth disparity maps directly from Light Detection and Ranging (LiDAR) and images to produce a large and diverse dataset for six aerial datasets across four different areas and two areas with different resolution images. We also introduce a LiDAR-to-image co-registration refinement to the framework that takes special precautions regarding occlusions and refrains from disparity interpolation to avoid precision loss. Evaluating 11 dense matching methods across datasets with diverse scene types, image resolutions, and geometric configurations, which are deeply investigated in dataset shift, GANet performs best with identical training and testing data, and PSMNet shows robustness across different datasets, and we proposed the best strategy for training with a limit dataset. We will also provide the dataset and training models; more information can be found at https://github.com/whuwuteng/Aerial_Stereo_Dataset.
Computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability distributions. In this context, we investigate the regression-by-classification paradigm which can represent multimodal distributions, without a prior assumption on the number of modes. Through experiments on a specifically designed synthetic dataset, we demonstrate that traditional loss functions lead to poor probability distribution estimates and severe overconfidence, in the absence of full ground truth distributions. In order to alleviate these issues, we propose hinge-Wasserstein -- a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training. This enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available. In extensive experiments, we show that the proposed loss leads to substantially better uncertainty estimation on two challenging computer vision tasks: horizon line detection and stereo disparity estimation.
This paper presents a novel approach for visible-thermal infrared stereoscopy, focusing on the estimation of disparities of human silhouettes. Visible-thermal infrared stereo poses several challenges, including occlusions and differently textured matching regions in both spectra. Finding matches between two spectra with varying colors, textures, and shapes adds further complexity to the task. To address the aforementioned challenges, this paper proposes a novel approach where a high-resolution convolutional neural network is used to better capture relationships between the two spectra. To do so, a modified HRNet backbone is used for feature extraction. This HRNet backbone is capable of capturing fine details and textures as it extracts features at multiple scales, thereby enabling the utilization of both local and global information. For matching visible and thermal infrared regions, our method extracts features on each patch using two modified HRNet streams. Features from the two streams are then combined for predicting the disparities by concatenation and correlation. Results on public datasets demonstrate the effectiveness of the proposed approach by improving the results by approximately 18 percentage points on the $\leq$ 1 pixel error, highlighting its potential for improving accuracy in this task. The code of VisiTherS is available on GitHub at the following link https://github.com/philippeDG/VisiTherS.
While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence, we introduce Spring $-$ a large, high-resolution, high-detail, computer-generated benchmark for scene flow, optical flow, and stereo. Based on rendered scenes from the open-source Blender movie "Spring", it provides photo-realistic HD datasets with state-of-the-art visual effects and ground truth training data. Furthermore, we provide a website to upload, analyze and compare results. Using a novel evaluation methodology based on a super-resolved UHD ground truth, our Spring benchmark can assess the quality of fine structures and provides further detailed performance statistics on different image regions. Regarding the number of ground truth frames, Spring is 60$\times$ larger than the only scene flow benchmark, KITTI 2015, and 15$\times$ larger than the well-established MPI Sintel optical flow benchmark. Initial results for recent methods on our benchmark show that estimating fine details is indeed challenging, as their accuracy leaves significant room for improvement. The Spring benchmark and the corresponding datasets are available at http://spring-benchmark.org.
Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network. Moreover, objects in the overlap region are often largely occluded or suffer from deformation due to camera distortion, causing a domain shift. To mitigate this issue, we propose using the following two main modules: (1) Stereo Disparity Estimation for Weak Depth Supervision and (2) Adversarial Overlap Region Discriminator. The former utilizes the traditional stereo disparity estimation method to obtain reliable disparity information from the overlap region. Given the disparity estimates as supervision, we propose regularizing the network to fully utilize the geometric potential of binocular images and improve the overall detection accuracy accordingly. Further, the latter module minimizes the representational gap between non-overlap and overlapping regions. We demonstrate the effectiveness of the proposed method with the nuScenes large-scale multi-view 3D object detection data. Our experiments show that our proposed method outperforms current state-of-the-art models, i.e., DETR3D and BEVDet.
Deep stereo matching has made significant progress in recent years. However, state-of-the-art methods are based on expensive 4D cost volume, which limits their use in real-world applications. To address this issue, 3D correlation maps and iterative disparity updates have been proposed. Regarding that in real-world platforms, such as self-driving cars and robots, the Lidar is usually installed. Thus we further introduce the sparse Lidar point into the iterative updates, which alleviates the burden of network updating the disparity from zero states. Furthermore, we propose training the network in a self-supervised way so that it can be trained on any captured data for better generalization ability. Experiments and comparisons show that the presented method is effective and achieves comparable results with related methods.
Stereo camera systems play an important role in robotics applications to perceive the 3D world. However, conventional cameras have drawbacks such as low dynamic range, motion blur and latency due to the underlying frame-based mechanism. Event cameras address these limitations as they report the brightness changes of each pixel independently with a fine temporal resolution, but they are unable to acquire absolute intensity information directly. Although integrated hybrid event-frame sensors (eg., DAVIS) are available, the quality of data is compromised by coupling at the pixel level in the circuit fabrication of such cameras. This paper proposes a stereo hybrid event-frame (SHEF) camera system that offers a sensor modality with separate high-quality pure event and pure frame cameras, overcoming the limitations of each separate sensor and allowing for stereo depth estimation. We provide a SHEF dataset targeted at evaluating disparity estimation algorithms and introduce a stereo disparity estimation algorithm that uses edge information extracted from the event stream correlated with the edge detected in the frame data. Our disparity estimation outperforms the state-of-the-art stereo matching algorithm on the SHEF dataset.
We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of RAFT-Stereo can perform accurate real-time inference. RAFT-stereo ranks first on the Middlebury leaderboard, outperforming the next best method on 1px error by 29% and outperforms all published work on the ETH3D two-view stereo benchmark. Code is available at https://github.com/princeton-vl/RAFT-Stereo.
Depth cameras have accelerated research in many areas of computer vision. Most triangulation-based depth cameras, whether structured light systems like the Kinect or active (assisted) stereo systems, are based on the principle of stereo matching. Depth from stereo is an active research topic dating back 30 years. Despite recent advances, algorithms usually trade-off accuracy for speed. In particular, efficient methods rely on fronto-parallel assumptions to reduce the search space and keep computation low. We present SOS (Slanted O(1) Stereo), the first algorithm capable of leveraging slanted support windows without sacrificing speed or accuracy. We use an active stereo configuration, where an illuminator textures the scene. Under this setting, local methods - such as PatchMatch Stereo - obtain state of the art results by jointly estimating disparities and slant, but at a large computational cost. We observe that these methods typically exploit local smoothness to simplify their initialization strategies. Our key insight is that local smoothness can in fact be used to amortize the computation not only within initialization, but across the entire stereo pipeline. Building on these insights, we propose a novel hierarchical initialization that is able to efficiently perform search over disparity and slants. We then show how this structure can be leveraged to provide high quality depth maps. Extensive quantitative evaluations demonstrate that the proposed technique yields significantly more precise results than current state of the art, but at a fraction of the computational cost. Our prototype implementation runs at 4000 fps on modern GPU architectures.
Conventional stereo suffers from a fundamental trade-off between imaging volume and signal-to-noise ratio (SNR) -- due to the conflicting impact of aperture size on both these variables. Inspired by the extended depth of field cameras, we propose a novel end-to-end learning-based technique to overcome this limitation, by introducing a phase mask at the aperture plane of the cameras in a stereo imaging system. The phase mask creates a depth-dependent point spread function, allowing us to recover sharp image texture and stereo correspondence over a significantly extended depth of field (EDOF) than conventional stereo. The phase mask pattern, the EDOF image reconstruction, and the stereo disparity estimation are all trained together using an end-to-end learned deep neural network. We perform theoretical analysis and characterization of the proposed approach and show a 6x increase in volume that can be imaged in simulation. We also build an experimental prototype and validate the approach using real-world results acquired using this prototype system.
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation. The underlying idea for the NAS algorithm is straightforward, namely, to enable the network the ability to choose among a set of operations (e.g., convolution with different filter sizes), one is able to find an optimal architecture that is better adapted to the problem at hand. However, so far the success of NAS has not been enjoyed by low-level geometric vision tasks such as stereo matching. This is partly due to the fact that state-of-the-art deep stereo matching networks, designed by humans, are already sheer in size. Directly applying the NAS to such massive structures is computationally prohibitive based on the currently available mainstream computing resources. In this paper, we propose the first end-to-end hierarchical NAS framework for deep stereo matching by incorporating task-specific human knowledge into the neural architecture search framework. Specifically, following the gold standard pipeline for deep stereo matching (i.e., feature extraction -- feature volume construction and dense matching), we optimize the architectures of the entire pipeline jointly. Extensive experiments show that our searched network outperforms all state-of-the-art deep stereo matching architectures and is ranked at the top 1 accuracy on KITTI stereo 2012, 2015 and Middlebury benchmarks, as well as the top 1 on SceneFlow dataset with a substantial improvement on the size of the network and the speed of inference. The code is available at https://github.com/XuelianCheng/LEAStereo.
We propose a method for fusing stereo disparity estimation with movement-induced prior information. Instead of independent inference frame-by-frame, we formulate the problem as a non-parametric learning task in terms of a temporal Gaussian process prior with a movement-driven kernel for inter-frame reasoning. We present a hierarchy of three Gaussian process kernels depending on the availability of motion information, where our main focus is on a new gyroscope-driven kernel for handheld devices with low-quality MEMS sensors, thus also relaxing the requirement of having full 6D camera poses available. We show how our method can be combined with two state-of-the-art deep stereo methods. The method either work in a plug-and-play fashion with pre-trained deep stereo networks, or further improved by jointly training the kernels together with encoder-decoder architectures, leading to consistent improvement.
We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. We show that imperceptible additive perturbations can significantly alter the disparity map, and correspondingly the perceived geometry of the scene. These perturbations not only affect the specific model they are crafted for, but transfer to models with different architecture, trained with different loss functions. We show that, when used for adversarial data augmentation, our perturbations result in trained models that are more robust, without sacrificing overall accuracy of the model. This is unlike what has been observed in image classification, where adding the perturbed images to the training set makes the model less vulnerable to adversarial perturbations, but to the detriment of overall accuracy. We test our method using the most recent stereo networks and evaluate their performance on public benchmark datasets.
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address this challenge by proposing a stereo matching network that considers pixel-wise matchability. Specifically, the network jointly regresses disparity and matchability maps from 3D probability volume through expectation and entropy operations. Next, a learned attenuation is applied as the robust loss function to alleviate the influence of weakly matchable pixels in the training. Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions. The proposed deep stereo matchability (DSM) framework can improve the matching result or accelerate the computation while still guaranteeing the quality. Moreover, the DSM framework is portable to many recent stereo networks. Extensive experiments are conducted on Scene Flow and KITTI stereo datasets to demonstrate the effectiveness of the proposed framework over the state-of-the-art learning-based stereo methods.
This paper presents HITNet, a novel neural network architecture for real-time stereo matching. Contrary to many recent neural network approaches that operate on a full cost volume and rely on 3D convolutions, our approach does not explicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometric propagation and warping mechanisms to infer disparity hypotheses. To achieve a high level of accuracy, our network not only geometrically reasons about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations. Our architecture is inherently multi-resolution allowing the propagation of information across different levels. Multiple experiments prove the effectiveness of the proposed approach at a fraction of the computation required by state-of-the-art methods. At the time of writing, HITNet ranks 1st-3rd on all the metrics published on the ETH3D website for two view stereo, ranks 1st on most of the metrics among all the end-to-end learning approaches on Middlebury-v3, ranks 1st on the popular KITTI 2012 and 2015 benchmarks among the published methods faster than 100ms.
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.