P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior

Deployment of depth estimating models in computer vision applications like obstacle avoidance, scene reconstruction, and camera pose estimation has become a fundamental task in the present day. Most of the depth images generated by existing monocular depth estimation models have blurry approximations of the depth and resolution, especially in low-textured regions. However, the existing depth estimation models that provide better predictions of depth generally take multiple images of the same scene as an input for generating depth maps. This paper presents a transfer learning approach with densely connected convolutional neural networks that take only an RGB image as an input for deeper and high-quality prediction of depth. In the proposed solution, an encoder-decoder architecture is leveraged for extracting features from an RGB image and generating a depth map for that corresponding RGB image. The densely connected convolutional network with 161 layers (Densenet-161) is used as an encoder, and the decoder is made up of five upsampling blocks and one transposed convolutional layer. The evaluation results obtained after training the model on the benchmark NYU V2 depth dataset ( Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor Segmentation and Support Inference from RGBD Images. In: Proceedings of the IEEE Conference on Computer Vision, pp. 746-760(2012).) have shown that the proposed approach for monocular depth estimation with the encoder-decoder architecture of lesser complexity, trained with fewer parameters and iterations, performs better than the existing state-of-the-art techniques as the value of the average Root Mean Square Error (RMSE) between the predicted and ground-truth depths, calculated in the evaluation phase of the proposed approach, is 0.505 which is less than the RMSE values obtained in case of all the mentioned monocular depth estimation methods. Furthermore, the depth maps generated by the proposed model have a good quality resolution and have minimal effect on the surrounding conditions like the texture of the walls, illumination effects, etc.

To take full advantage of the information of images captured by drones and given that most existing monocular depth estimation methods based on supervised learning require vast quantities of corresponding ground truth depth data for training, the model of unsupervised monocular depth estimation based on residual neural network of coarse–refined feature extractions for drone is therefore proposed. As a virtual camera is introduced through a deep residual convolution neural network based on coarse–refined feature extractions inspired by the principle of binocular depth estimation, the unsupervised monocular depth estimation has become an image reconstruction problem. To improve the performance of our model for monocular depth estimation, the following innovations are proposed. First, the pyramid processing for input image is proposed to build the topological relationship between the resolution of input image and the depth of input image, which can improve the sensitivity of depth information from a single image and reduce the impact of input image resolution on depth estimation. Second, the residual neural network of coarse–refined feature extractions for corresponding image reconstruction is designed to improve the accuracy of feature extraction and solve the contradiction between the calculation time and the numbers of network layers. In addition, to predict high detail output depth maps, the long skip connections between corresponding layers in the neural network of coarse feature extractions and deconvolution neural network of refined feature extractions are designed. Third, the loss of corresponding image reconstruction based on the structural similarity index (SSIM), the loss of approximate disparity smoothness and the loss of depth map are united as a novel training loss to better train our model. The experimental results show that our model has superior performance on the KITTI dataset composed by corresponding left view and right view and Make3D dataset composed by image and corresponding ground truth depth map compared to the state-of-the-art monocular depth estimation methods and basically meet the requirements for depth information of images captured by drones when our model is trained on KITTI.

Depth estimation is an essential component in understanding the 3D geometry of a scene. In comparison to traditional depth estimation methods such as structure from motion and stereo vision matching, determining depth relation using a single camera is challenging. The recent advancements in convolutional neural networks have accelerated the research in monocular depth estimation. However, most technologies infer depth maps using lower resolution images due to network capacity and complexity issues. Another challenge in depth estimation is ambiguous and sparse depth maps. These issues are caused due to labeling errors, hardware faults, or occlusions. This paper presents a novel end-to-end trainable convolutional neural network architecture – depth transverse transformer network (DTTNet). The proposed network is designed and optimized to perform monocular depth estimation. This network aims at exploring the multi-resolution representation to perform pixel-wise depth estimation more accurately. In order to improve the accuracy of depth estimation, different kinds of ad hoc networks are proposed subsequently. Extensive computer simulations on NYU Depth V2 and SUN RGB-D dataset demonstrate the effectiveness of the proposed DTTNet against state-of-the-art methods. DTTNet can potentially optimize depth perception in intelligent systems such as automated driving and video surveillance applications, computational photography, and augmented reality. The source code is available at https://github.com/shreyaskamathkm/DTTNet

SABV-Depth: A biologically inspired deep learning network for monocular depth estimation

Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.

Self-supervised monocular depth estimation can exhibit excellent performance in static environments due to the multi-view consistency assumption during the training process. However, it is hard to maintain depth consistency in dynamic scenes when considering the occlusion problem caused by moving objects. For this reason, we propose a method of self-supervised self-distillation for monocular depth estimation (SS-MDE) in dynamic scenes, where a deep network with a multi-scale decoder and a lightweight pose network are designed to predict depth in a self-supervised manner via the disparity, motion information, and the association between two adjacent frames in the image sequence. Meanwhile, in order to improve the depth estimation accuracy of static areas, the pseudo-depth images generated by the LeReS network are used to provide the pseudo-supervision information, enhancing the effect of depth refinement in static areas. Furthermore, a forgetting factor is leveraged to alleviate the dependency on the pseudo-supervision. In addition, a teacher model is introduced to generate depth prior information, and a multi-view mask filter module is designed to implement feature extraction and noise filtering. This can enable the student model to better learn the deep structure of dynamic scenes, enhancing the generalization and robustness of the entire model in a self-distillation manner. Finally, on four public data datasets, the performance of the proposed SS-MDE method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy () of 89% while minimizing the error (AbsRel) by 0.102 in NYU-Depth V2 and achieving an accuracy () of 87% while minimizing the error (AbsRel) by 0.111 in KITTI.

Monocular depth estimation with boundary attention mechanism and Shifted Window Adaptive Bins

Structure perception and edge refinement network for monocular depth estimation

Recently, significant progress has been achieved in developing deep learning-based approaches for estimating depth maps from monocular images. However, many existing methods rely on content and structure information extracted from RGB photographs, which often results in inaccurate depth estimation, particularly for regions with low texture or occlusions. To overcome these limitations, we propose a novel method that exploits contextual semantic information to predict precise depth maps from monocular images. Our approach leverages a deep autoencoder network incorporating high-quality semantic features from the state-of-the-art HRNet-v2 semantic segmentation model. By feeding the autoencoder network with these features, our method can effectively preserve the discontinuities of the depth images and enhance monocular depth estimation. Specifically, we exploit the semantic features related to the localization and boundaries of the objects in the image to improve the accuracy and robustness of the depth estimation. To validate the effectiveness of our approach, we tested our model on two publicly available datasets, NYU Depth v2 and SUN RGB-D. Our method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy of 85%, while minimizing the error Rel by 0.12, RMS by 0.523, and log10 by 0.0527. Our approach also demonstrated exceptional performance in preserving object boundaries and faithfully detecting small object structures in the scene.

Monocular depth estimation with guidance of surface normal map

<p>Monocular depth estimation is a fundamental challenge since the foundation of computer vision with many real-world applications. Recently, the introduction of Deep Convolutional Neural Networks (CNN) has brought significant improvements to this particular problem. There are many solutions for scene depth estimation with a focus on obtaining high-quality depth maps from a given RGB image. The insertion of prior information by adding a smoothing regularization has improved the results. However, the smoothing of the surfaces comes together with a certain degradation of the edges. The goal of this paper is to make a comparison between various regularization terms used either in supervised or self-supervised learning methods. In addition to this, we modified the regularization term used currently in self-supervised methods such to work in a supervised manner. The experimental results on NYU-Depth v2 have shown that the regularization based on L1 norm of the gradient is the best and the self-supervised modified one outperforms the rest. Finally, rather than relying on common evaluation metrics, we used an additional accuracy measure based on the Steerable Pyramid and Kullback-Leibler divergence (KLD) for edge accuracy of estimated depths that is more sensitive to positional errors of the edges.</p>

Self-supervised monocular depth estimation has been widely investigated to estimate depth images and relative poses from RGB images. This framework is promising because the depth and pose networks can be trained from just time-sequence images without the need for the ground truth depth and poses. In this work, we estimate the depth around a robot (360° view) using time-sequence spherical camera images, from a camera whose parameters are unknown. We propose a learnable axisymmetric camera model which accepts distorted spherical camera images with two fisheye camera images as well as pinhole camera images. In addition, we trained our models with a photo-realistic simulator to generate ground truth depth images to provide supervision. Moreover, we introduced loss functions to provide floor constraints to reduce artifacts that can result from reflective floor surfaces. We demonstrate the efficacy of our method using the spherical camera images from the GO Stanford dataset and pinhole camera images from the KITTI dataset to compare our method's performance with that of baseline method in learning the camera parameters.

Stereoscopic display technology plays a significant role in industries, such as film, television and autonomous driving. The accuracy of depth estimation is crucial for achieving high-quality and realistic stereoscopic display effects. In addressing the inherent challenges of applying Transformers to depth estimation, the Stereoscopic Pyramid Transformer-Depth (SPT-Depth) is introduced. This method utilizes stepwise downsampling to acquire both shallow and deep semantic information, which are subsequently fused. The training process is divided into fine and coarse convergence stages, employing distinct training strategies and hyperparameters, resulting in a substantial reduction in both training and validation losses. In the training strategy, a shift and scale-invariant mean square error function is employed to compensate for the lack of translational invariance in the Transformers. Additionally, an edge-smoothing function is applied to reduce noise in the depth map, enhancing the model's robustness. The SPT-Depth achieves a global receptive field while effectively reducing time complexity. In comparison with the baseline method, with the New York University Depth V2 (NYU Depth V2) dataset, there is a 10% reduction in Absolute Relative Error (Abs Rel) and a 36% decrease in Root Mean Square Error (RMSE). When compared with the state-of-the-art methods, there is a 17% reduction in RMSE.

Monocular depth estimation infers 3D geometric structures of scenes from a single RGB image, offering significant applications in autonomous driving, robot navigation, and other fields. While current self-supervised learning methods avoid dependency on ground truth depth data, they still exhibit no-table limitations in complex scenarios: traditional encoder-decoder architec-tures inevitably lose high-frequency detail features when acquiring global context through continuous downsampling, resulting in blurred edges and texture distortion in depth maps. To alleviate these issues, we propose a nov-el approach named HyperDetailNet, which significantly enhances depth es-timation detail preservation. Specifically, our method contains two key com-ponents: 1 A dual-branch detail-global feature extraction network, where the detail branch adopts an enlarge-then-reduce strategy to preserve high-frequency texture information, while the global branch extracts overall struc-tural information of the scene. 2 To effectively fuse features from both branches, we designed a multi-attention fusion module that combines spatial attention, channel attention, and sliding window self-attention mechanisms to enhance model perception of detailed regions. Experimental results demonstrate that HyperDetailNet achieves excellent performance on both KITTI and Make3D datasets, with significant improvements in depth estima-tion for edge and texture-rich areas. Additionally, ablation experiments veri-fy the effectiveness of the dual-branch detail-global feature extraction DepthNet and multi-attention fusion module.

Monocular depth estimation is an essential task for scene understanding. The underlying structure of objects and stuff in a complex scene is critical to recovering accurate and visually-pleasing depth maps. Global structure conveys scene layouts, while local structure reflects shape details. Recently developed approaches based on convolutional neural networks (CNNs) significantly improve the performance of depth estimation. However, few of them take into account multi-scale structures in complex scenes. In this paper, we propose a Structure-Aware Residual Pyramid Network (SARPN) to exploit multi-scale structures for accurate depth prediction. We propose a Residual Pyramid Decoder (RPD) which expresses global scene structure in upper levels to represent layouts, and local structure in lower levels to present shape details. At each level, we propose Residual Refinement Modules (RRM) that predict residual maps to progressively add finer structures on the coarser structure predicted at the upper level. In order to fully exploit multi-scale image features, an Adaptive Dense Feature Fusion (ADFF) module, which adaptively fuses effective features from all scales for inferring structures of each scale, is introduced. Experiment results on the challenging NYU-Depth v2 dataset demonstrate that our proposed approach achieves state-of-the-art performance in both qualitative and quantitative evaluation. The code is available at https://github.com/Xt-Chen/SARPN.