Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning. While previous surveys in the late 2010s covered the first stage of this revolution, the last five years of research brought further ground-breaking advancements to the field. This paper aims to fill this gap in a two-fold manner: first, we offer an in-depth examination of the latest developments in deep stereo matching, focusing on the pioneering architectural designs and groundbreaking paradigms that have redefined the field in the 2020s; second, we present a thorough analysis of the critical challenges that have emerged alongside these advances, providing a comprehensive taxonomy of these issues and exploring the state-of-the-art techniques proposed to address them. By reviewing both the architectural innovations and the key challenges, we offer a holistic view of deep stereo matching and highlight the specific areas that require further investigation. To accompany this survey, we maintain a regularly updated project page that catalogs papers on deep stereo matching in our Awesome-Deep-Stereo-Matching (https://github.com/fabiotosi92/Awesome-Deep-Stereo-Matching) repository.
We study the 3D object understanding task for manipulating everyday objects with different material properties (diffuse, specular, transparent and mixed). Existing monocular and RGB-D methods suffer from scale ambiguity due to missing or imprecise depth measurements. We present CODERS, a one-stage approach for Category-level Object Detection, pose Estimation and Reconstruction from Stereo images. The base of our pipeline is an implicit stereo matching module that combines stereo image features with 3D position information. Concatenating this presented module and the following transform-decoder architecture leads to end-to-end learning of multiple tasks required by robot manipulation. Our approach significantly outperforms all competing methods in the public TOD dataset. Furthermore, trained on simulated data, CODERS generalize well to unseen category-level object instances in real-world robot manipulation experiments. Our dataset, code, and demos will be available on our project page.
We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision. As it is well-known that stereo matching boils down to a per-pixel disparity estimation problem, the popular state-of-the-art stereo-matching approaches widely rely on regressing the scene disparity values, yet via discretization of scene disparity values. Such discretization often fails to capture the nuanced, continuous nature of scene depth. Stereo Risk departs from the conventional discretization approach by formulating the scene disparity as an optimal solution to a continuous risk minimization problem, hence the name "stereo risk". We demonstrate that $L^1$ minimization of the proposed continuous risk function enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions. Furthermore, to enable the end-to-end network training of the non-differentiable $L^1$ risk optimization, we exploited the implicit function theorem, ensuring a fully differentiable network. A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets, including KITTI 2012, KITTI 2015, ETH3D, SceneFlow, and Middlebury 2014.
We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating computationally intensive 4D costs, LightStereo adopts the 3D cost volume as a lightweight alternative. While similar approaches have been explored previously, our breakthrough lies in enhancing performance through a dedicated focus on the channel dimension of the 3D cost volume, where the distribution of matching costs is encapsulated. Our exhaustive exploration has yielded plenty of strategies to amplify the capacity of the pivotal dimension, ensuring both precision and efficiency. We compare the proposed LightStereo with existing state-of-the-art methods across various benchmarks, which demonstrate its superior performance in speed, accuracy, and resource utilization. LightStereo achieves a competitive EPE metric in the SceneFlow datasets while demanding a minimum of only 22 GFLOPs and 17 ms of runtime, and ranks 1st on KITTI 2015 among real-time models. Our comprehensive analysis reveals the effect of 2D cost aggregation for stereo matching, paving the way for real-world applications of efficient stereo systems. Code will be available at \url{https://github.com/XiandaGuo/OpenStereo}.
Both uncertainty-assisted and iteration-based methods have achieved great success in stereo matching. However, existing uncertainty estimation methods take a single image and the corresponding disparity as input, which imposes higher demands on the estimation network. In this paper, we propose Cost volume-based disparity Uncertainty Estimation (UEC). Based on the rich similarity information in the cost volume coming from the image pairs, the proposed UEC can achieve competitive performance with low computational cost. Secondly, we propose two methods of uncertainty-assisted disparity estimation, Uncertainty-based Disparity Rectification (UDR) and Uncertainty-based Disparity update Conditioning (UDC). These two methods optimise the disparity update process of the iterative-based approach without adding extra parameters. In addition, we propose Disparity Rectification loss that significantly improves the accuracy of small amount of disparity updates. We present a high-performance stereo architecture, DR Stereo, which is a combination of the proposed methods. Experimental results from SceneFlow, KITTI, Middlebury 2014, and ETH3D show that DR-Stereo achieves very competitive disparity estimation performance.
Due to the difficulty in obtaining real samples and ground truth, the generalization performance and domain adaptation performance are critical for the feasibility of stereo matching methods in practical applications. However, there are significant distributional discrepancies among different domains, which pose challenges for generalization and domain adaptation of the model. Inspired by the iteration-based methods, we propose a novel stepwise regression architecture. This architecture regresses the disparity error through multiple range-controlled clips, which effectively overcomes domain discrepancies. We implement this architecture based on the iterative-based methods, and refer to this new stereo method as SR-Stereo. Specifically, a new stepwise regression unit is proposed to replace the original update unit in order to control the range of output. Meanwhile, a regression objective segment is proposed to set the supervision individually for each stepwise regression unit. In addition, to enhance the edge awareness of models adapting new domains with sparse ground truth, we propose Domain Adaptation based on Pre-trained Edges (DAPE). In DAPE, a pre-trained stereo model and an edge estimator are used to estimate the edge maps of the target domain images, which along with the sparse ground truth disparity are used to fine-tune the stereo model. The proposed SR-Stereo and DAPE are extensively evaluated on SceneFlow, KITTI, Middbury 2014 and ETH3D. Compared with the SOTA methods and generalized methods, the proposed SR-Stereo achieves competitive in-domain and cross-domain performances. Meanwhile, the proposed DAPE significantly improves the performance of the fine-tuned model, especially in the texture-less and detailed regions.
Due to the high similarity of disparity between consecutive frames in video sequences, the area where disparity changes is defined as the residual map, which can be calculated. Based on this, we propose RecSM, a network based on residual estimation with a flexible recursive structure for video stereo matching. The RecSM network accelerates stereo matching using a Multi-scale Residual Estimation Module (MREM), which employs the temporal context as a reference and rapidly calculates the disparity for the current frame by computing only the residual values between the current and previous frames. To further reduce the error of estimated disparities, we use the Disparity Optimization Module (DOM) and Temporal Attention Module (TAM) to enforce constraints between each module, and together with MREM, form a flexible Stackable Computation Structure (SCS), which allows for the design of different numbers of SCS based on practical scenarios. Experimental results demonstrate that with a stack count of 3, RecSM achieves a 4x speed improvement compared to ACVNet, running at 0.054 seconds based on one NVIDIA RTX 2080TI GPU, with an accuracy decrease of only 0.7%. Code is available at https://github.com/Y0uchenZ/RecSM.
We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary views of the scene to guide the disparity estimation, effectively reducing the search space for matches. This approach is specifically tailored to stereo rigs in volumetric capture systems, where an accurate depth plays a key role in the downstream reconstruction task. To enable training and regression at high resolutions targeted by recent systems, our approach extends a sparse correlation computation into a hybrid sparse-dense scheme suitable for application in leading recurrent network architectures. We evaluate the performance-efficiency trade-off of our method compared to state-of-the-art methods, and demonstrate the efficacy of the visual hull guidance. In addition, we propose a training scheme for a further reduction of memory requirements during optimization, facilitating training on high-resolution data.
Depth estimation based on stereo matching is a classic but popular computer vision problem, which has a wide range of real-world applications. Current stereo matching methods generally adopt the deep Siamese neural network architecture, and have achieved impressing performance by constructing feature matching cost volumes and using 3D convolutions for cost aggregation. However, most existing methods suffer from large number of parameters and slow running time due to the sequential use of 3D convolutions. In this paper, we propose Ghost-Stereo, a novel end-to-end stereo matching network. The feature extraction part of the network uses the GhostNet to form a U-shaped structure. The core of Ghost-Stereo is a GhostNet feature-based cost volume enhancement (Ghost-CVE) module and a GhostNet-inspired lightweight cost volume aggregation (Ghost-CVA) module. For the Ghost-CVE part, cost volumes are constructed and fused by the GhostNet-based features to enhance the spatial context awareness. For the Ghost-CVA part, a lightweight 3D convolution bottleneck block based on the GhostNet is proposed to reduce the computational complexity in this module. By combining with the context and geometry fusion module, a classical hourglass-shaped cost volume aggregate structure is constructed. Ghost-Stereo achieves a comparable performance than state-of-the-art real-time methods on several publicly benchmarks, and shows a better generalization ability.
In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the improvements are only modest. In this paper, we propose a novel strategy by incorporating knowledge distillation and model pruning to overcome the inherent trade-off between speed and accuracy. As a result, we obtained a model that maintains real-time performance while delivering high accuracy on edge devices. Our proposed method involves three key steps. Firstly, we review state-of-the-art methods and design our lightweight model by removing redundant modules from those efficient models through a comparison of their contributions. Next, we leverage the efficient model as the teacher to distill knowledge into the lightweight model. Finally, we systematically prune the lightweight model to obtain the final model. Through extensive experiments conducted on two widely-used benchmarks, Sceneflow and KITTI, we perform ablation studies to analyze the effectiveness of each module and present our state-of-the-art results.
Remote sensing (RS) images are important to monitor and survey earth at varying spatial scales. Continuous observations from various RS sources complement single observations to improve applications. Fusion into single or multiple images provides more informative, accurate, complete, and coherent data. Studies intensively investigated spatial-temporal fusion for specific applications like pan-sharpening and spatial-temporal fusion for time-series analysis. Fusion methods can process different images, modalities, and tasks and are expected to be robust and adaptive to various types of images (e.g., spectral images, classification maps, and elevation maps) and scene complexities. This work presents solutions to improve existing fusion methods that process gridded data and consider their type-specific uncertainties. The contributions include: 1) A spatial-temporal filter that addresses spectral heterogeneity of multitemporal images. 2) 3D iterative spatiotemporal filter that enhances spatiotemporal inconsistencies of classification maps. 3) Adaptive semantic-guided fusion that enhances the accuracy of DSMs and compares them with traditional fusion approaches to show the significance of adaptive methods. 4) A comprehensive analysis of DL stereo matching methods against traditional Census-SGM to obtain detailed knowledge on the accuracy of the DSMs at the stereo matching level. We analyze the overall performance, robustness, and generalization capability, which helps identify the limitations of current DSM generation methods. 5) Based on previous analysis, we develop a novel finetuning strategy to enhance transferability of DL stereo matching methods, hence, the accuracy of DSMs. Our work shows the importance of spatial, temporal, and geometric fusion in enhancing RS applications. It shows that the fusion problem is case-specific and depends on the image type, scene content, and application.
In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera images. Since recent stereo matching has demonstrated accurate geometry prediction, we introduce stereo matching into novel-view synthesis for high-quality geometry reconstruction. To this end, this paper proposes a novel framework, dubbed StereoNeRF, which integrates stereo matching into a NeRF-based generalizable view synthesis approach. StereoNeRF is equipped with three key components to effectively exploit stereo matching in novel-view synthesis: a stereo feature extractor, a depth-guided plane-sweeping, and a stereo depth loss. Moreover, we propose the StereoNVS dataset, the first multi-view dataset of stereo-camera images, encompassing a wide variety of both real and synthetic scenes. Our experimental results demonstrate that StereoNeRF surpasses previous approaches in generalizable view synthesis.
With the development of remote sensing technology in recent decades, spaceborne sensors with sub-meter and meter spatial resolution (Worldview and PlanetScope) have achieved a considerable image quality to generate 3D geospatial data via a stereo matching pipeline. These achievements have significantly increased the data accessibility in 3D, necessitating adapting these 3D geospatial data to analyze human and natural environments. This dissertation explores several novel approaches based on stereo and multi-view satellite image-derived 3D geospatial data, to deal with remote sensing application issues for built-up area modeling and natural environment monitoring, including building model 3D reconstruction, glacier dynamics tracking, and lake algae monitoring. Specifically, the dissertation introduces four parts of novel approaches that deal with the spatial and temporal challenges with satellite-derived 3D data. The first study advances LoD-2 building modeling from satellite-derived Orthophoto and DSMs with a novel approach employing a model-driven workflow that generates building rectangular 3D geometry models. Secondly, we further enhanced our building reconstruction framework for dense urban areas and non-rectangular purposes, we implemented deep learning for unit-level segmentation and introduced a gradient-based circle reconstruction for circular buildings to develop a polygon composition technique for advanced building LoD2 reconstruction. Our third study utilizes high-spatiotemporal resolution PlanetScope satellite imagery for glacier tracking at 3D level in mid-latitude regions. Finally, we proposed a term as "Algal Behavior Function" to refine the quantification of chlorophyll-a concentrations from satellite imagery in water quality monitoring, addressing algae fluctuations and timing discrepancies between satellite observations and field measurements, thus enhancing the precision of underwater algae volume estimates. Overall, this dissertation demonstrates the extensive potential of satellite photogrammetry applications in addressing urban and environmental challenges. It further showcases innovative analytical methodologies that enhance the applicability of adapting stereo and multi-view very high-resolution satellite-derived 3D data. (See full abstract in the document)
In the field of remote sensing, the scarcity of stereo-matched and particularly lack of accurate ground truth data often hinders the training of deep neural networks. The use of synthetically generated images as an alternative, alleviates this problem but suffers from the problem of domain generalization. Unifying the capabilities of image-to-image translation and stereo-matching presents an effective solution to address the issue of domain generalization. Current methods involve combining two networks, an unpaired image-to-image translation network and a stereo-matching network, while jointly optimizing them. We propose an edge-aware GAN-based network that effectively tackles both tasks simultaneously. We obtain edge maps of input images from the Sobel operator and use it as an additional input to the encoder in the generator to enforce geometric consistency during translation. We additionally include a warping loss calculated from the translated images to maintain the stereo consistency. We demonstrate that our model produces qualitatively and quantitatively superior results than existing models, and its applicability extends to diverse domains, including autonomous driving.
Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal and disparity outputs. Unlike standard recurrent units, we employ Agent Attention to generate more expressive features. We also designed an attention-based context network to capture a large amount of contextual information. Experiments on several public benchmarks show that we have achieved competitive stereo matching performance. Our model ranks first in the Scene Flow dataset, achieving over a 7% improvement compared to competing methods, and requires only 8 iterations to achieve state-of-the-art results.
Accurate and dense depth estimation with stereo cameras and LiDAR is an important task for automatic driving and robotic perception. While sparse hints from LiDAR points have improved cost aggregation in stereo matching, their effectiveness is limited by the low density and non-uniform distribution. To address this issue, we propose a novel stereo-LiDAR depth estimation network with Semi-Dense hint Guidance, named SDG-Depth. Our network includes a deformable propagation module for generating a semi-dense hint map and a confidence map by propagating sparse hints using a learned deformable window. These maps then guide cost aggregation in stereo matching. To reduce the triangulation error in depth recovery from disparity, especially in distant regions, we introduce a disparity-depth conversion module. Our method is both accurate and efficient. The experimental results on benchmark tests show its superior performance. Our code is available at https://github.com/SJTU-ViSYS/SDG-Depth.
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.
Road surface conditions, especially geometry profiles, enormously affect driving performance of autonomous vehicles. Vision-based online road reconstruction promisingly captures road information in advance. Existing solutions like monocular depth estimation and stereo matching suffer from modest performance. The recent technique of Bird's-Eye-View (BEV) perception provides immense potential to more reliable and accurate reconstruction. This paper uniformly proposes two simple yet effective models for road elevation reconstruction in BEV named RoadBEV-mono and RoadBEV-stereo, which estimate road elevation with monocular and stereo images, respectively. The former directly fits elevation values based on voxel features queried from image view, while the latter efficiently recognizes road elevation patterns based on BEV volume representing correlation between left and right voxel features. Insightful analyses reveal their consistence and difference with the perspective view. Experiments on real-world dataset verify the models' effectiveness and superiority. Elevation errors of RoadBEV-mono and RoadBEV-stereo achieve 1.83 cm and 0.50 cm, respectively. Our models are promising for practical road preview, providing essential information for promoting safety and comfort of autonomous vehicles. The code is released at https://github.com/ztsrxh/RoadBEV
We propose a method for estimating disparity confidence intervals in stereo matching problems. Confidence intervals provide complementary information to usual confidence measures. To the best of our knowledge, this is the first method creating disparity confidence intervals based on the cost volume. This method relies on possibility distributions to interpret the epistemic uncertainty of the cost volume. Our method has the benefit of having a white-box nature, differing in this respect from current state-of-the-art deep neural networks approaches. The accuracy and size of confidence intervals are validated using the Middlebury stereo datasets as well as a dataset of satellite images. This contribution is freely available on GitHub.
Stereo matching has become a key technique for 3D environment perception in intelligent vehicles. For a considerable time, convolutional neural networks (CNNs) have remained the mainstream choice for feature extraction in this domain. Nonetheless, there is a growing consensus that the existing paradigm should evolve towards vision foundation models (VFM), particularly those developed based on vision Transformers (ViTs) and pre-trained through self-supervision on extensive, unlabeled datasets. While VFMs are adept at extracting informative, general-purpose visual features, specifically for dense prediction tasks, their performance often lacks in geometric vision tasks. This study serves as the first exploration of a viable approach for adapting VFMs to stereo matching. Our ViT adapter, referred to as ViTAS, is constructed upon three types of modules: spatial differentiation, patch attention fusion, and cross-attention. The first module initializes feature pyramids, while the latter two aggregate stereo and multi-scale contextual information into fine-grained features, respectively. ViTAStereo, which combines ViTAS with cost volume-based stereo matching back-end processes, achieves the top rank on the KITTI Stereo 2012 dataset and outperforms the second-best network StereoBase by approximately 7.9% in terms of the percentage of error pixels, with a tolerance of 3 pixels. Additional experiments across diverse scenarios further demonstrate its superior generalizability compared to all other state-of-the-art approaches. We believe this new paradigm will pave the way for the next generation of stereo matching networks.