Self-supervised Monocular Depth Estimation Research Articles

Shufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation

Abstract Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost and extended effective distance compared with alternative methods. However, like automated guided vehicles, devices with limited computing resources struggle to leverage state-of-the-art large model structures. In recent years, researchers have acknowledged this issue and endeavored to reduce model size. Model lightweight techniques aim to decrease the number of parameters while maintaining satisfactory performance. In this paper, to enhance the model’s performance in lightweight scenarios, a novel approach to encompassing three key aspects is proposed: (1) utilizing LeakyReLU to involve more neurons in manifold representation; (2) employing large convolution for improved recognition of edges in lightweight models; (3) applying channel grouping and shuffling to maximize the model efficiency. Experimental results demonstrate that our proposed method achieves satisfactory outcomes on KITTI and Make3D benchmarks while having only 1.6M trainable parameters, representing a reduction of 27% compared with the previous smallest model, Lite-Mono-tiny, in monocular depth estimation.

Complete contextual information extraction for self-supervised monocular depth estimation

Self-supervised learning methods are increasingly important for monocular depth estimation since they do not require ground-truth data during training. Although existing methods have achieved great success for better monocular depth estimation based on Convolutional Neural Networks (CNNs), the limited receptive field of CNNs usually is insufficient to effectively model the global information, e.g., relationship between foreground and background or relationship among objects, which are crucial for accurately capturing scene structure. Recently, some studies based on Transformers have attracted significant interest in computer vision. However, duo to the lack of spatial locality bias, they may fail to model the local information, e.g., fine-grained details with an image. To tackle these issues, we propose a novel self-supervised learning framework by incorporating the advantages of both the CNNs and Transformers so as to model the complete contextual information for high-quality monocular depth estimation. Specifically, the proposed method mainly includes two branches, where the Transformer branch is considered to capture the global information while the Convolution branch is exploited to preserve the local information. We also design a rectangle convolution module with pyramid structure to perceive the semi-global information, e.g. thin objects, along the horizontal and vertical directions within an image. Moreover, we propose a shape refinement module by learning the affinity matrix between pixel and its neighborhood to obtain accurate geometrical structure of scenes. Extensive experiments evaluated on KITTI, Cityscapes and Make3D dataset demonstrate that the proposed method achieves the competitive result compared with the state-of-the-art self-supervised monocular depth estimation methods and shows good cross-dataset generalization ability.

F[formula omitted]Depth: Self-supervised indoor monocular depth estimation via optical flow consistency and feature map synthesis

Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently suffer from severe performance drop for indoor scenes, where low-textured regions dominant in the scenes are almost indiscriminative. To address the issue, we propose a self-supervised indoor monocular depth estimation framework called F2Depth. A self-supervised optical flow estimation network is introduced to supervise depth learning. To improve optical flow estimation performance in low-textured areas, only some patches of points with more discriminative features are adopted for finetuning based on our well-designed patch-based photometric loss. The finetuned optical flow estimation network generates high-accuracy optical flow as a supervisory signal for depth estimation. Correspondingly, an optical flow consistency loss is designed. Multi-scale feature maps produced by finetuned optical flow estimation network perform warping to compute feature map synthesis loss as another supervisory signal for depth learning. Experimental results on the NYU Depth V2 dataset demonstrate the effectiveness of the framework and our proposed losses. To evaluate the generalization ability of our F2Depth, we collect a Campus Indoor depth dataset composed of approximately 1500 points selected from 99 images in 18 scenes. Zero-shot generalization experiments on 7-Scenes dataset and Campus Indoor achieve δ1 accuracy of 75.8% and 76.0% respectively. The accuracy results show that our model can generalize well to monocular images captured in unknown indoor scenes.

Self-supervised monocular depth estimation on water scenes via specular reflection prior

Monocular depth estimation from a single image is an ill-posed problem for computer vision due to insufficient reliable cues as the prior knowledge. Besides the inter-frame supervision, namely stereo and adjacent frames, extensive prior information is available in the same frame. Reflections from specular surfaces, informative intra-frame priors, enable us to reformulate the ill-posed depth estimation task as a multi-view synthesis. This paper proposes the first self-supervision for deep-learning depth estimation on water scenes via intra-frame priors, known as reflection supervision and geometrical constraints. In the first stage, a water segmentation network is performed to separate the reflection components from the entire image. Next, we construct a self-supervised framework to predict the target appearance from reflections, perceived as other perspectives. The photometric re-projection error, incorporating SmoothL1 and a novel photometric adaptive SSIM, is formulated to optimize pose and depth estimation by aligning the transformed virtual depths and source ones. As a supplement, the water surface is determined from real and virtual camera positions, which complement the depth of the water area. Furthermore, to alleviate these laborious ground truth annotations, we introduce a large-scale water reflection scene (WRS) dataset rendered from Unreal Engine 4. Extensive experiments on the WRS dataset prove the feasibility of the proposed method compared to state-of-the-art depth estimation techniques.

TAMDepth: self-supervised monocular depth estimation with transformer and adapter modulation

TAMDepth: self-supervised monocular depth estimation with transformer and adapter modulation

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to the lack of explicit 3D supervision and imprecise camera poses, resulting in suboptimal outcomes. To tackle these issues, we propose AltNeRF---a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. SMDE in AltNeRF masterfully learns depth and pose priors to regulate NeRF training. The depth prior enriches NeRF's capacity for precise scene geometry depiction, while the pose prior provides a robust starting point for subsequent pose refinement. Moreover, we introduce an alternating algorithm that harmoniously melds NeRF outputs into SMDE through a consistence-driven mechanism, thus enhancing the integrity of depth priors. This alternation empowers AltNeRF to progressively refine NeRF representations, yielding the synthesis of realistic novel views. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.

PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimation

Self-supervised monocular depth estimation is of significant importance with applications spanning across autonomous driving and robotics. However, the reliance on self-supervision introduces a strong static-scene assumption, thereby posing challenges in achieving optimal performance in dynamic scenes, which are prevalent in most real-world situations. To address these issues, we propose PPEA-Depth, a Progressive Parameter-Efficient Adaptation approach to transfer a pre-trained image model for self-supervised depth estimation. The training comprises two sequential stages: an initial phase trained on a dataset primarily composed of static scenes, succeeded by an expansion to more intricate datasets involving dynamic scenes. To facilitate this process, we design compact encoder and decoder adapters to enable parameter-efficient tuning, allowing the network to adapt effectively. They not only uphold generalized patterns from pre-trained image models but also retain knowledge gained from the preceding phase into the subsequent one. Extensive experiments demonstrate that PPEA-Depth achieves state-of-the-art performance on KITTI, CityScapes and DDAD datasets.

SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation

Recently, self-supervised monocular depth estimation has gained popularity with numerous applications in autonomous driving and robotics. However, existing solutions primarily seek to estimate depth from immediate visual features, and struggle to recover fine-grained scene details. In this paper, we introduce SQLdepth, a novel approach that can effectively learn fine-grained scene structure priors from ego-motion. In SQLdepth, we propose a novel Self Query Layer (SQL) to build a self-cost volume and infer depth from it, rather than inferring depth from feature maps. We show that, the self-cost volume is an effective inductive bias for geometry learning, which implicitly models the single-frame scene geometry, with each slice of it indicating a relative distance map between points and objects in a latent space. Experimental results on KITTI and Cityscapes show that our method attains remarkable state-of-the-art performance, and showcases computational efficiency, reduced training complexity, and the ability to recover fine-grained scene details. Moreover, the self-matching-oriented relative distance querying in SQL improves the robustness and zero-shot generalization capability of SQLdepth. Code is available at https://github.com/hisfog/SfMNeXt-Impl.

On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation

On Robust Cross-view Consistency in Self-supervised Monocular Depth Estimation

A Foggy Weather Simulation Algorithm for Traffic Image Synthesis Based on Monocular Depth Estimation.

This study addresses the ongoing challenge for learning-based methods to achieve accurate object detection in foggy conditions. In response to the scarcity of foggy traffic image datasets, we propose a foggy weather simulation algorithm based on monocular depth estimation. The algorithm involves a multi-step process: a self-supervised monocular depth estimation network generates a relative depth map and then applies dense geometric constraints for scale recovery to derive an absolute depth map. Subsequently, the visibility of the simulated image is defined to generate a transmittance map. The dark channel map is then used to distinguish sky regions and estimate atmospheric light values. Finally, the atmospheric scattering model is used to generate fog simulation images under specified visibility conditions. Experimental results show that more than 90% of fog images have AuthESI values of less than 2, which indicates that their non-structural similarity (NSS) characteristics are very close to those of natural fog. The proposed fog simulation method is able to convert clear images in natural environments, providing a solution to the problem of lack of foggy image datasets and incomplete visibility data.

Bridging local and global representations for self-supervised monocular depth estimation

Monocular depth estimation is a challenging problem, especially in a self-supervised manner without relying on the depth ground truth. The self-supervised approach places higher demands on the global and local feature extraction capabilities of the network. Based on this view, we propose to perform efficient hybrid feature extraction by exploiting the capacity of the Transformer and convolutional neural network to model long-range dependencies and local correlations at the same time. A bowknot-type fuser is designed to align features extracted from different sources as well as bridge global and local semantic representations. To obtain higher-quality pseudo-labels from the extracted features, we suggest the pseudo-label smoothing technique to fully utilize the multi-scale features, consequently boosting the effect of self-distillation loss as an auxiliary supervision to train the neural network. In addition, we propose pixel adaptive smoothness loss to refine the predicted depth map by introducing the image’s textural and spatial information. The suggested method is trained on the KITTI benchmark using stereo image pairs and achieves competitive depth estimation performance in contrast with previous approaches. The code and models are available at https://github.com/MaylingLin/BLGR-Depth.

Self-Supervised Monocular Depth Estimation Based on High-Order Spatial Interactions

Self-Supervised Monocular Depth Estimation Based on High-Order Spatial Interactions

Dual-attention-based semantic-aware self-supervised monocular depth estimation

Dual-attention-based semantic-aware self-supervised monocular depth estimation

IterDepth: Iterative Residual Refinement for Outdoor Self-Supervised Multi-Frame Monocular Depth Estimation

Self-supervised monocular depth estimation has been a challenging task in computer vision for a long time, and it relies on only monocular or stereo video for its supervision. To address the challenge, we propose a novel multi-frame monocular depth estimation method called IterDepth, which is based on an iterative residual refinement network. IterDepth extracts depth features from consecutive frames and computes a 3D cost volume measuring the difference between current and previous features transformed by PoseCNN (pose estimation convolutional neural network). We reformulate depth prediction as a residual learning problem, revamping the dominating depth regression to enable high-accuracy multi-frame monocular depth estimation. Specifically, we design a gated recurrent depth fusion unit that seamlessly blends depth features from the cost volume, image features, and the depth prediction. The unit updates the hidden states and refines the depth map through iterative refinement, achieving more accurate predictions than existing methods. Our experiments on the KITTI dataset demonstrate that IterDepth is 7× faster in terms of FPS (frames per second) than the recent state-of-the-art DepthFormer model with competitive performance. We also test IterDepth on the Cityscapes dataset to showcase its generalization capability in other real-world environments. Moreover, IterDepth can balance accuracy and computational efficiency by adjusting the number of refinement iterations and performs competitively with other CNN-based monocular depth estimation approaches. Code will be made publicly available.

Learn to Adapt for Self-Supervised Monocular Depth Estimation.

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress by virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed on other new datasets due to the gap between different datasets. Though some methods utilize domain adaptation technologies to jointly train different domains and narrow the gap between them, the trained models cannot generalize to new domains that are not involved in training. To boost the transferability of self-supervised monocular depth estimation models and mitigate the issue of meta-overfitting, we train the model in the pipeline of meta-learning and propose an adversarial depth estimation task. We adopt model-agnostic meta-learning (MAML) to obtain universal initial parameters for further adaptation and train the network in an adversarial manner to extract domain-invariant representations for easing meta-overfitting. In addition, we propose a constraint to impose upon cross-task depth consistency to compel the depth estimation to be identical in different adversarial tasks, which improves the performance of our method and smoothens the training process. Experiments on four new datasets demonstrate that our method adapts quite fast to new domains. Our method trained after 0.5 epoch achieves comparable results with the state-of-the-art methods trained at least 20 epochs.

Self-Supervised Monocular Depth Estimation With Self-Perceptual Anomaly Handling.

It is attractive to extract plausible 3-D information from a single 2-D image, and self-supervised learning has shown impressive potential in this field. However, when only monocular videos are available as training data, moving objects at similar speeds to the camera can disturb the reprojection process during training. Existing methods filter out some moving pixels by comparing pixelwise photometric error, but the illumination inconsistency between frames leads to incomplete filtering. In addition, existing methods calculate photometric error within local windows, which leads to the fact that even if an anomalous pixel is masked out, it can still implicitly disturb the reprojection process, as long as it is in the local neighborhood of a nonanomalous pixel. Moreover, the ill-posed nature of monocular depth estimation makes the same scene correspond to multiple plausible depth maps, which damages the robustness of the model. In order to alleviate the above problems, we propose: 1) a self-reprojection mask to further filter out moving objects while avoiding illumination inconsistency; 2) a self-statistical mask method to prevent the filtered anomalous pixels from implicitly disturbing the reprojection; and 3) a self-distillation augmentation consistency loss to reduce the impact of ill-posed nature of monocular depth estimation. Our method shows superior performance on the KITTI dataset, especially when evaluating only the depth of potential moving objects.

SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes.

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms.

Self-Supervised Monocular Depth Estimation from Videos via Adaptive Reconstruction Constraints

Self-Supervised Monocular Depth Estimation from Videos via Adaptive Reconstruction Constraints

Self-Supervised Monocular Depth Estimation With Positional Shift Depth Variance and Adaptive Disparity Quantization.

Recently, attempts to learn the underlying 3D structures of a scene from monocular videos in a fully self-supervised fashion have drawn much attention. One of the most challenging aspects of this task is to handle independently moving objects as they break the rigid-scene assumption. In this paper, we show for the first time that pixel positional information can be exploited to learn SVDE (Single View Depth Estimation) from videos. The proposed moving object (MO) masks, which are induced by the depth variance to shifted positional information (SPI) and are referred to as 'SPIMO' masks, are highly robust and consistently remove independently moving objects from the scenes, allowing for robust and consistent learning of SVDE from videos. Additionally, we introduce a new adaptive quantization scheme that assigns the best per-pixel quantization curve for depth discretization, improving the fine granularity and accuracy of the final aggregated depth maps. Finally, we employ existing boosting techniques in a new way that self-supervises moving object depths further. With these features, our pipeline is robust against moving objects and generalizes well to high-resolution images, even when trained with small patches, yielding state-of-the-art (SOTA) results with four- to eight-fold fewer parameters than the previous SOTA techniques that learn from videos. We present extensive experiments on KITTI and CityScapes that show the effectiveness of our method.

Spatial-Aware Dynamic Lightweight Self-Supervised Monocular Depth Estimation

Spatial-Aware Dynamic Lightweight Self-Supervised Monocular Depth Estimation