Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture search (NAS) approaches, where finding optimized networks are computationally highly demanding, the introduced novel Assisted Tabu Search leads to efficient architecture exploration. Moreover, we construct the search space on a pre-defined backbone network to balance layer diversity and search space size. The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance. The LiDNAS optimized models achieve results superior to compact depth estimation state-of-the-art on NYU-Depth-v2, KITTI, and ScanNet, while being 7%-500% more compact in size, i.e the number of model parameters.
Deep neural networks have recently thrived on single image depth estimation. That being said, current developments on this topic highlight an apparent compromise between accuracy and network size. This work proposes an accurate and lightweight framework for monocular depth estimation based on a self-attention mechanism stemming from salient point detection. Specifically, we utilize a sparse set of keypoints to train a FuSaNet model that consists of two major components: Fusion-Net and Saliency-Net. In addition, we introduce a normalized Hessian loss term invariant to scaling and shear along the depth direction, which is shown to substantially improve the accuracy. The proposed method achieves state-of-the-art results on NYU-Depth-v2 and KITTI while using 3.1-38.4 times smaller model in terms of the number of parameters than baseline approaches. Experiments on the SUN-RGBD further demonstrate the generalizability of the proposed method.
Depth estimation is a long-lasting yet important task in computer vision. Most of the previous works try to estimate depth from input images and assume images are all-in-focus (AiF), which is less common in real-world applications. On the other hand, a few works take defocus blur into account and consider it as another cue for depth estimation. In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack). We design a shared architecture to exploit the relationship between depth and AiF estimation. As a result, the proposed method can be trained either supervisedly with ground truth depth, or \emph{unsupervisedly} with AiF images as supervisory signals. We show in various experiments that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.
Estimating a scene's depth to achieve collision avoidance against moving pedestrians is a crucial and fundamental problem in the robotic field. This paper proposes a novel, low complexity network architecture for fast and accurate human depth estimation and segmentation in indoor environments, aiming to applications for resource-constrained platforms (including battery-powered aerial, micro-aerial, and ground vehicles) with a monocular camera being the primary perception module. Following the encoder-decoder structure, the proposed framework consists of two branches, one for depth prediction and another for semantic segmentation. Moreover, network structure optimization is employed to improve its forward inference speed. Exhaustive experiments on three self-generated datasets prove our pipeline's capability to execute in real-time, achieving higher frame rates than contemporary state-of-the-art frameworks (114.6 frames per second on an NVIDIA Jetson Nano GPU with TensorRT) while maintaining comparable accuracy.
Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue raises problems when the model needs to be deployed on resource-limited devices. For this, we propose two light models for stereo vision with reduced complexity and without sacrificing accuracy. Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively. To this end, we leverage 2D MobileNet blocks and extend them to 3D for stereo vision application. Besides, a new cost volume is proposed to boost the accuracy of the 2D model, making it performing close to 3D networks. Experiments show that the proposed 2D/3D networks effectively reduce the computational expense (27%/95% and 72%/38% fewer parameters/operations in 2D and 3D models, respectively) while upholding the accuracy. Our code is available at https://github.com/cogsys-tuebingen/mobilestereonet.
3D detection plays an indispensable role in environment perception. Due to the high cost of commonly used LiDAR sensor, stereo vision based 3D detection, as an economical yet effective setting, attracts more attention recently. For these approaches based on 2D images, accurate depth information is the key to achieve 3D detection, and most existing methods resort to a preliminary stage for depth estimation. They mainly focus on the global depth and neglect the property of depth information in this specific task, namely, sparsity and locality, where exactly accurate depth is only needed for these 3D bounding boxes. Motivated by this finding, we propose a stereo-image based anchor-free 3D detection method, called structure-aware stereo 3D detector (termed as SIDE), where we explore the instance-level depth information via constructing the cost volume from RoIs of each object. Due to the information sparsity of local cost volume, we further introduce match reweighting and structure-aware attention, to make the depth information more concentrated. Experiments conducted on the KITTI dataset show that our method achieves the state-of-the-art performance compared to existing methods without depth map supervision.
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, especially in weak texture regions and at object boundaries. To overcome this weakness, we propose novel ideas to improve self-supervised monocular depth estimation by leveraging cross-domain information, especially scene semantics. We focus on incorporating implicit semantic knowledge into geometric representation enhancement and suggest two ideas: a metric learning approach that exploits the semantics-guided local geometry to optimize intermediate depth representations and a novel feature fusion module that judiciously utilizes cross-modality between two heterogeneous feature representations. We comprehensively evaluate our methods on the KITTI dataset and demonstrate that our method outperforms state-of-the-art methods. The source code is available at https://github.com/hyBlue/FSRE-Depth.
To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps fusion. Recent studies concentrate on deep neural architectures for depth estimation by using conventional depth fusion method or direct 3D reconstruction network by regressing Truncated Signed Distance Function (TSDF). In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results. As mentioned, our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume. In order to improve the matching performance between images acquired from very different viewpoints (e.g., large-baseline and rotations), we introduce a rotation-invariant 3D convolution kernel called PosedConv. The effectiveness of the proposed architecture is underlined via a large series of experiments conducted on the ScanNet dataset where our approach compares favorably against both traditional and deep learning techniques.
Self-supervised monocular depth estimation has achieved impressive performance on outdoor datasets. Its performance however degrades notably in indoor environments because of the lack of textures. Without rich textures, the photometric consistency is too weak to train a good depth network. Inspired by the early works on indoor modeling, we leverage the structural regularities exhibited in indoor scenes, to train a better depth network. Specifically, we adopt two extra supervisory signals for self-supervised training: 1) the Manhattan normal constraint and 2) the co-planar constraint. The Manhattan normal constraint enforces the major surfaces (the floor, ceiling, and walls) to be aligned with dominant directions. The co-planar constraint states that the 3D points be well fitted by a plane if they are located within the same planar region. To generate the supervisory signals, we adopt two components to classify the major surface normal into dominant directions and detect the planar regions on the fly during training. As the predicted depth becomes more accurate after more training epochs, the supervisory signals also improve and in turn feedback to obtain a better depth model. Through extensive experiments on indoor benchmark datasets, the results show that our network outperforms the state-of-the-art methods. The source code is available at https://github.com/SJTU-ViSYS/StructDepth .
Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for depth estimation are limited due to large noise, low accuracy, and strict requirements for multi-camera calibration. In this work, for a unified surrounding perception, we introduce panoramic images to obtain larger field of view. We extend PADENet first appeared in our previous conference work for outdoor scene understanding, to perform panoramic monocular depth estimation with a focus for indoor scenes. At the same time, we improve the training process of the neural network adapted to the characteristics of panoramic images. In addition, we fuse traditional stereo matching algorithm with deep learning methods and further improve the accuracy of depth predictions. With a comprehensive variety of experiments, this research demonstrates the effectiveness of our schemes aiming for indoor scene perception.
Lensless cameras provide a framework to build thin imaging systems by replacing the lens in a conventional camera with an amplitude or phase mask near the sensor. Existing methods for lensless imaging can recover the depth and intensity of the scene, but they require solving computationally-expensive inverse problems. Furthermore, existing methods struggle to recover dense scenes with large depth variations. In this paper, we propose a lensless imaging system that captures a small number of measurements using different patterns on a programmable mask. In this context, we make three contributions. First, we present a fast recovery algorithm to recover textures on a fixed number of depth planes in the scene. Second, we consider the mask design problem, for programmable lensless cameras, and provide a design template for optimizing the mask patterns with the goal of improving depth estimation. Third, we use a refinement network as a post-processing step to identify and remove artifacts in the reconstruction. These modifications are evaluated extensively with experimental results on a lensless camera prototype to showcase the performance benefits of the optimized masks and recovery algorithms over the state of the art.
In this paper, we present a system for incrementally reconstructing a dense 3D model of the geometry of an outdoor environment using a single monocular camera attached to a moving vehicle. Dense models provide a rich representation of the environment facilitating higher-level scene understanding, perception, and planning. Our system employs dense depth prediction with a hybrid mapping architecture combining state-of-the-art sparse features and dense fusion-based visual SLAM algorithms within an integrated framework. Our novel contributions include design of hybrid sparse-dense camera tracking and loop closure, and scale estimation improvements in dense depth prediction. We use the motion estimates from the sparse method to overcome the large and variable inter-frame displacement typical of outdoor vehicle scenarios. Our system then registers the live image with the dense model using whole-image alignment. This enables the fusion of the live frame and dense depth prediction into the model. Global consistency and alignment between the sparse and dense models are achieved by applying pose constraints from the sparse method directly within the deformation of the dense model. We provide qualitative and quantitative results for both trajectory estimation and surface reconstruction accuracy, demonstrating competitive performance on the KITTI dataset. Qualitative results of the proposed approach are illustrated in https://youtu.be/Pn2uaVqjskY. Source code for the project is publicly available at the following repository https://github.com/robotvisionmu/DenseMonoSLAM.
Remarkable results have been achieved by DCNN based self-supervised depth estimation approaches. However, most of these approaches can only handle either day-time or night-time images, while their performance degrades for all-day images due to large domain shift and the variation of illumination between day and night images. To relieve these limitations, we propose a domain-separated network for self-supervised depth estimation of all-day images. Specifically, to relieve the negative influence of disturbing terms (illumination, etc.), we partition the information of day and night image pairs into two complementary sub-spaces: private and invariant domains, where the former contains the unique information (illumination, etc.) of day and night images and the latter contains essential shared information (texture, etc.). Meanwhile, to guarantee that the day and night images contain the same information, the domain-separated network takes the day-time images and corresponding night-time images (generated by GAN) as input, and the private and invariant feature extractors are learned by orthogonality and similarity loss, where the domain gap can be alleviated, thus better depth maps can be expected. Meanwhile, the reconstruction and photometric losses are utilized to estimate complementary information and depth maps effectively. Experimental results demonstrate that our approach achieves state-of-the-art depth estimation results for all-day images on the challenging Oxford RobotCar dataset, proving the superiority of our proposed approach.
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These two-stage detectors improve with the accuracy of the intermediate depth estimation network, which can itself be improved without manual labels via large-scale self-supervised learning. However, they tend to suffer from overfitting more than end-to-end methods, are more complex, and the gap with similar lidar-based detectors remains significant. In this work, we propose an end-to-end, single stage, monocular 3D object detector, DD3D, that can benefit from depth pre-training like pseudo-lidar methods, but without their limitations. Our architecture is designed for effective information transfer between depth estimation and 3D detection, allowing us to scale with the amount of unlabeled pre-training data. Our method achieves state-of-the-art results on two challenging benchmarks, with 16.34% and 9.28% AP for Cars and Pedestrians (respectively) on the KITTI-3D benchmark, and 41.5% mAP on NuScenes.
We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e.g., a department store or a metro station. Our approach predicts absolute scale depth maps over the entire scene consisting of a static background and multiple moving people, by training on dynamic scenes. Since it is difficult to collect dense depth maps from crowded indoor environments, we design our training framework without requiring depths produced from depth sensing devices. Our network leverages RGB images and sparse depth maps generated from traditional 3D reconstruction methods to estimate dense depth maps. We use two constraints to handle depth for non-rigidly moving people without tracking their motion explicitly. We demonstrate that our approach offers consistent improvements over recent depth estimation methods on the NAVERLABS dataset, which includes complex and crowded scenes.
Deep networks for Monocular Depth Estimation (MDE) have achieved promising performance recently and it is of great importance to further understand the interpretability of these networks. Existing methods attempt to provide posthoc explanations by investigating visual cues, which may not explore the internal representations learned by deep networks. In this paper, we find that some hidden units of the network are selective to certain ranges of depth, and thus such behavior can be served as a way to interpret the internal representations. Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units. Moreover, we then propose a method to train interpretable MDE deep networks without changing their original architectures, by assigning a depth range for each unit to select. Experimental results demonstrate that our method is able to enhance the interpretability of deep MDE networks by largely improving the depth selectivity of their units, while not harming or even improving the depth estimation accuracy. We further provide a comprehensive analysis to show the reliability of selective units, the applicability of our method on different layers, models, and datasets, and a demonstration on analysis of model error. Source code and models are available at https://github.com/youzunzhi/InterpretableMDE .
Vision transformers have attracted much attention from computer vision researchers as they are not restricted to the spatial inductive bias of ConvNets. However, although Transformer-based backbones have achieved much progress on ImageNet classification, it is still unclear whether the learned representations are as transferable as or even more transferable than ConvNets' features. To address this point, we systematically investigate the transfer learning ability of ConvNets and vision transformers in 15 single-task and multi-task performance evaluations. Given the strong correlation between the performance of pre-trained models and transfer learning, we include 2 residual ConvNets (i.e., R-101x3 and R-152x4) and 3 Transformer-based visual backbones (i.e., ViT-B, ViT-L and Swin-B), which have close error rates on ImageNet, that indicate similar transfer learning performance on downstream datasets. We observe consistent advantages of Transformer-based backbones on 13 downstream tasks (out of 15), including but not limited to fine-grained classification, scene recognition (classification, segmentation and depth estimation), open-domain classification, face recognition, etc. More specifically, we find that two ViT models heavily rely on whole network fine-tuning to achieve performance gains while Swin Transformer does not have such a requirement. Moreover, vision transformers behave more robustly in multi-task learning, i.e., bringing more improvements when managing mutually beneficial tasks and reducing performance losses when tackling irrelevant tasks. We hope our discoveries can facilitate the exploration and exploitation of vision transformers in the future.
Many camera sensors use a dual-pixel (DP) design that operates as a rudimentary light field providing two sub-aperture views of a scene in a single capture. The DP sensor was developed to improve how cameras perform autofocus. Since the DP sensor's introduction, researchers have found additional uses for the DP data, such as depth estimation, reflection removal, and defocus deblurring. We are interested in the latter task of defocus deblurring. In particular, we propose a single-image deblurring network that incorporates the two sub-aperture views into a multi-task framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network's ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task. Our dataset, code, and trained models are publicly available at https://github.com/Abdullah-Abuolaim/multi-task-defocus-deblurring-dual-pixel-nimat.
Location and appearance are the key cues for video object segmentation. Many sources such as RGB, depth, optical flow and static saliency can provide useful information about the objects. However, existing approaches only utilize the RGB or RGB and optical flow. In this paper, we propose a novel multi-source fusion network for zero-shot video object segmentation. With the help of interoceptive spatial attention module (ISAM), spatial importance of each source is highlighted. Furthermore, we design a feature purification module (FPM) to filter the inter-source incompatible features. By the ISAM and FPM, the multi-source features are effectively fused. In addition, we put forward an automatic predictor selection network (APS) to select the better prediction of either the static saliency predictor or the moving object predictor in order to prevent over-reliance on the failed results caused by low-quality optical flow maps. Extensive experiments on three challenging public benchmarks (i.e. DAVIS$_{16}$, Youtube-Objects and FBMS) show that the proposed model achieves compelling performance against the state-of-the-arts. The source code will be publicly available at \textcolor{red}{\url{https://github.com/Xiaoqi-Zhao-DLUT/Multi-Source-APS-ZVOS}}.