Semantic segmentation has achieved remarkable progress but remains challenging due to the complex scene, object occlusion, and so on. Some research works have attempted to use extra information such as a depth map to help RGB based semantic segmentation because the depth map could provide complementary geometric cues. However, due to the inaccessibility of depth sensors, depth information is usually unavailable for the test images. In this paper, we leverage only the depth of training images as the privileged information to mine the hard pixels in semantic segmentation, in which depth information is only available for training images but not available for test images. Specifically, we propose a novel Loss Weight Module, which outputs a loss weight map by employing two depth-related measurements of hard pixels: Depth Prediction Error and Depthaware Segmentation Error. The loss weight map is then applied to segmentation loss, with the goal of learning a more robust model by paying more attention to the hard pixels. Besides, we also explore a curriculum learning strategy based on the loss weight map. Meanwhile, to fully mine the hard pixels on different scales, we apply our loss weight module to multi-scale side outputs. Our hard pixels mining method achieves the state-of-the-art results on two benchmark datasets, and even outperforms the methods which need depth input during testing.
We present a versatile formulation of the convolution operation that we term a "mapped convolution." The standard convolution operation implicitly samples the pixel grid and computes a weighted sum. Our mapped convolution decouples these two components, freeing the operation from the confines of the image grid and allowing the kernel to process any type of structured data. As a test case, we demonstrate its use by applying it to dense inference on spherical data. We perform an in-depth study of existing spherical image convolution methods and propose an improved sampling method for equirectangular images. Then, we discuss the impact of data discretization when deriving a sampling function, highlighting drawbacks of the cube map representation for spherical data. Finally, we illustrate how mapped convolutions enable us to convolve directly on a mesh by projecting the spherical image onto a geodesic grid and training on the textured mesh. This method exceeds the state of the art for spherical depth estimation by nearly 17%. Our findings suggest that mapped convolutions can be instrumental in expanding the application scope of convolutional neural networks.
This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available. Existing datasets, such as the KITTI benchmark, provide only sparse reference measurements with an order of magnitude lower angular resolution - these sparse measurements are treated as ground truth by existing depth estimation methods. We propose an evaluation methodology in four characteristic automotive scenarios recorded in varying weather conditions (day, night, fog, rain). As a result, our benchmark allows us to evaluate the robustness of depth sensing methods in adverse weather and different driving conditions. Using the proposed evaluation data, we demonstrate that current stereo approaches provide significantly more stable depth estimates than monocular methods and lidar completion in adverse weather. Data and code are available at https://github.com/gruberto/PixelAccurateDepthBenchmark.git.
Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accurately in some of the challenging scenes. The encoder-decoder network has been widely used in the depth estimation and the RCNN has brought significant improvements in the ego-motion estimation. Furthermore, the latest use of Generative Adversarial Nets(GANs) in depth and ego-motion estimation has demonstrated that the estimation could be further improved by generating pictures in the game learning process. This paper proposes a novel unsupervised network system for visual depth and ego-motion estimation: Stacked Generative Adversarial Network(SGANVO). It consists of a stack of GAN layers, of which the lowest layer estimates the depth and ego-motion while the higher layers estimate the spatial features. It can also capture the temporal dynamic due to the use of a recurrent representation across the layers. See Fig.1 for details. We select the most commonly used KITTI [1] data set for evaluation. The evaluation results show that our proposed method can produce better or comparable results in depth and ego-motion estimation.
This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3-5) color images from uncalibrated sparse views as input, which greatly simplifies data acquisition and extends applicable scenarios. Since different views have limited overlaps, our method allows a single image as input to discern the depth and semantic information of the scene. The key issue is how to recover relatively accurate depth from single images and reconstruct a 3D scene by fusing very few depth maps. To address this problem, we first design an iterative deep architecture, IterNet, that estimates depth and semantic segmentation alternately, so that they benefit each other. To deal with the little overlap and non-rigid transformation between views, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information from sparse views. We also make available a new indoor synthetic dataset simultaneously providing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts, useful for training and evaluation. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors and better 3D reconstruction results, compared with state-of-the-art methods.
Detecting objects such as cars and pedestrians in 3D plays an indispensable role in autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for accurate depth information. While recently pseudo-LiDAR has been introduced as a promising alternative, at a much lower cost based solely on stereo images, there is still a notable performance gap. In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation. Concretely, we adapt the stereo network architecture and loss function to be more aligned with accurate depth estimation of faraway objects --- currently the primary weakness of pseudo-LiDAR. Further, we explore the idea to leverage cheaper but extremely sparse LiDAR sensors, which alone provide insufficient information for 3D detection, to de-bias our depth estimation. We propose a depth-propagation algorithm, guided by the initial depth estimates, to diffuse these few exact measurements across the entire depth map. We show on the KITTI object detection benchmark that our combined approach yields substantial improvements in depth estimation and stereo-based 3D object detection --- outperforming the previous state-of-the-art detection accuracy for faraway objects by 40%. Our code is available at https://github.com/mileyan/Pseudo_Lidar_V2.
We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [AAAI'19]. Code and models have been open sourced at https://sites.google.com/corp/view/struct2depth.
Beyond depth estimation from a single image, the monocular cue is useful in a broader range of depth inference applications and settings---such as when one can leverage other available depth cues for improved accuracy. Currently, different applications, with different inference tasks and combinations of depth cues, are solved via different specialized networks---trained separately for each application. Instead, we propose a versatile task-agnostic monocular model that outputs a probability distribution over scene depth given an input color image, as a sample approximation of outputs from a patch-wise conditional VAE. We show that this distributional output can be used to enable a variety of inference tasks in different settings, without needing to retrain for each application. Across a diverse set of applications (depth completion, user guided estimation, etc.), our common model yields results with high accuracy---comparable to or surpassing that of state-of-the-art methods dependent on application-specific networks.
In this paper, we introduce the problem of estimating the real world depth of elements in a scene captured by two cameras with different field of views, where the first field of view (FOV) is a Wide FOV (WFOV) captured by a wide angle lens, and the second FOV is contained in the first FOV and is captured by a tele zoom lens. We refer to the problem of estimating the inverse depth for the union of FOVs, while leveraging the stereo information in the overlapping FOV, as Tele-Wide Stereo Matching (TW-SM). We propose different deep learning solutions to the TW-SM problem. Since the disparity is proportional to the inverse depth, we train stereo matching disparity estimation (SMDE) networks to estimate the disparity for the union WFOV. We further propose an end-to-end deep multitask tele-wide stereo matching neural network (MT-TW-SMNet), which simultaneously learns the SMDE task for the overlapped Tele FOV and the single image inverse depth estimation (SIDE) task for the WFOV. Moreover, we design multiple methods for the fusion of the SMDE and SIDE networks. We evaluate the performance of TW-SM on the popular KITTI and SceneFlow stereo datasets, and demonstrate its practicality by synthesizing the Bokeh effect on the WFOV from a tele-wide stereo image pair.
Single image depth estimation (SIDE) plays a crucial role in 3D computer vision. In this paper, we propose a two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes. At the first stage, the scene understanding module will categorize the RGB image into different depth-ranges. We introduce two different scene understanding modules based on scene classification and coarse depth estimation respectively. At the second stage, SIDE networks trained by the images of specific depth-range are applied to obtain an accurate depth map. In order to improve the accuracy, we further design a multi-task encoding-decoding SIDE network DS-SIDENet based on depthwise separable convolutions. DS-SIDENet is optimized to minimize both depth classification and depth regression losses. This improves the accuracy compared to a single-task SIDE network. Experimental results demonstrate that training DS-SIDENet on an individual dataset such as NYU achieves competitive performance to the state-of-art methods with much better efficiency. Ours proposed robust SIDE framework also shows good performance for the ScanNet indoor images and KITTI outdoor images simultaneously. It achieves the top performance compared to the Robust Vision Challenge (ROB) 2018 submissions.
A crucial component of an autonomous vehicle (AV) is the artificial intelligence (AI) is able to drive towards a desired destination. Today, there are different paradigms addressing the development of AI drivers. On the one hand, we find modular pipelines, which divide the driving task into sub-tasks such as perception and maneuver planning and control. On the other hand, we find end-to-end driving approaches that try to learn a direct mapping from input raw sensor data to vehicle control signals. The later are relatively less studied, but are gaining popularity since they are less demanding in terms of sensor data annotation. This paper focuses on end-to-end autonomous driving. So far, most proposals relying on this paradigm assume RGB images as input sensor data. However, AVs will not be equipped only with cameras, but also with active sensors providing accurate depth information (e.g., LiDARs). Accordingly, this paper analyses whether combining RGB and depth modalities, i.e. using RGBD data, produces better end-to-end AI drivers than relying on a single modality. We consider multimodality based on early, mid and late fusion schemes, both in multisensory and single-sensor (monocular depth estimation) settings. Using the CARLA simulator and conditional imitation learning (CIL), we show how, indeed, early fusion multimodality outperforms single-modality.
Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground truth depth-maps, supervised learning techniques such as direct depth regression cannot be used. In this paper, we propose an unsupervised method for depth estimation from a single underwater image taken `in the wild' by using haze as a cue for depth. Our approach is based on indirect depth-map estimation where we learn the mapping functions between unpaired RGB-D terrestrial images and arbitrary underwater images to estimate the required depth-map. We propose a method which is based on the principles of cycle-consistent learning and uses dense-block based auto-encoders as generator networks. We evaluate and compare our method both quantitatively and qualitatively on various underwater images with diverse attenuation and scattering conditions and show that our method produces state-of-the-art results for unsupervised depth estimation from a single underwater image.
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and output, such as high-resolution image and video segmentation or 3D medical imaging, has been limited by various factors. Primarily, in the training stage, it is necessary to store network activations for back propagation. In these settings, the memory requirements associated with storing activations can exceed what is feasible with current hardware, especially for problems in 3D. Motivated by the propagation of signals over physical networks, that are governed by the hyperbolic Telegraph equation, in this work we introduce a fully conservative hyperbolic network for problems with high dimensional input and output. We introduce a coarsening operation that allows completely reversible CNNs by using a learnable Discrete Wavelet Transform and its inverse to both coarsen and interpolate the network state and change the number of channels. We show that fully reversible networks are able to achieve results comparable to the state of the art in 4D time-lapse hyper spectral image segmentation and full 3D video segmentation, with a much lower memory footprint that is a constant independent of the network depth. We also extend the use of such networks to Variational Auto Encoders with high resolution input and output.
We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a least squares solution for the inverse 2D to 3D geometric mapping problem, using the camera projection matrix. The closed-form solution of the mathematical system, along with the initial output of the adapted Faster R-CNN are then passed through a final ShiftNet network that refines the result using our newly proposed Volume Displacement Loss. Our novel, geometrically constrained deep learning approach to monocular 3D object detection obtains top results on KITTI 3D Object Detection Benchmark, being the best among all monocular methods that do not use any pre-trained network for depth estimation.
In this work, we exploit a depth estimation Fully Convolutional Residual Neural Network (FCRN) for in-air perspective images to estimate the depth of underwater perspective and omni-directional images. We train one conventional and one spherical FCRN for underwater perspective and omni-directional images, respectively. The spherical FCRN is derived from the perspective FCRN via a spherical longitude-latitude mapping. For that, the omni-directional camera is modeled as a sphere, while images captured by it are displayed in the longitude-latitude form. Due to the lack of underwater datasets, we synthesize images in both data-driven and theoretical ways, which are used in training and testing. Finally, experiments are conducted on these synthetic images and results are displayed in both qualitative and quantitative way. The comparison between ground truth and the estimated depth map indicates the effectiveness of our method.
We introduce SharpNet, a method that predicts an accurate depth map for an input color image, with a particular attention to the reconstruction of occluding contours: Occluding contours are an important cue for object recognition, and for realistic integration of virtual objects in Augmented Reality, but they are also notoriously difficult to reconstruct accurately. For example, they are a challenge for stereo-based reconstruction methods, as points around an occluding contour are visible in only one image. Inspired by recent methods that introduce normal estimation to improve depth prediction, we introduce a novel term that constrains depth and occluding contours predictions. Since ground truth depth is difficult to obtain with pixel-perfect accuracy along occluding contours, we use synthetic images for training, followed by fine-tuning on real data. We demonstrate our approach on the challenging NYUv2-Depth dataset, and show that our method outperforms the state-of-the-art along occluding contours, while performing on par with the best recent methods for the rest of the images. Its accuracy along the occluding contours is actually better than the `ground truth' acquired by a depth camera based on structured light. We show this by introducing a new benchmark based on NYUv2-Depth for evaluating occluding contours in monocular reconstruction, which is our second contribution.
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be unsupervised using stereo image pairs, supervised using LiDAR point clouds, or semi-supervised using both stereo and LiDAR. In general, semi-supervised training is preferred as it does not suffer from the weaknesses of either supervised training, resulting from the difference in the cameras and the LiDARs field of view, or unsupervised training, resulting from the poor depth accuracy that can be recovered from a stereo pair. In this paper, we present our research in single image depth prediction using semi-supervised training that outperforms the state-of-the-art. We achieve this through a loss function that explicitly exploits left-right consistency in a stereo reconstruction, which has not been adopted in previous semi-supervised training. In addition, we describe the correct use of ground truth depth derived from LiDAR that can significantly reduce prediction error. The performance of our depth prediction model is evaluated on popular datasets, and the importance of each aspect of our semi-supervised training approach is demonstrated through experimental results. Our deep neural network model has been made publicly available.
Deep neural networks have lead to a breakthrough in depth estimation from single images. Recent work often focuses on the accuracy of the depth map, where an evaluation on a publicly available test set such as the KITTI vision benchmark is often the main result of the article. While such an evaluation shows how well neural networks can estimate depth, it does not show how they do this. To the best of our knowledge, no work currently exists that analyzes what these networks have learned. In this work we take the MonoDepth network by Godard et al. and investigate what visual cues it exploits for depth estimation. We find that the network ignores the apparent size of known obstacles in favor of their vertical position in the image. Using the vertical position requires the camera pose to be known; however we find that MonoDepth only partially corrects for changes in camera pitch and roll and that these influence the estimated depth towards obstacles. We further show that MonoDepth's use of the vertical image position allows it to estimate the distance towards arbitrary obstacles, even those not appearing in the training set, but that it requires a strong edge at the ground contact point of the object to do so. In future work we will investigate whether these observations also apply to other neural networks for monocular depth estimation.
Convolutional neural networks (CNNs) have emerged as the state-of-the-art in multiple vision tasks including depth estimation. However, memory and computing power requirements remain as challenges to be tackled in these models. Monocular depth estimation has significant use in robotics and virtual reality that requires deployment on low-end devices. Training a small model from scratch results in a significant drop in accuracy and it does not benefit from pre-trained large models. Motivated by the literature of model pruning, we propose a lightweight monocular depth model obtained from a large trained model. This is achieved by removing the least important features with a novel joint end-to-end filter pruning. We propose to learn a binary mask for each filter to decide whether to drop the filter or not. These masks are trained jointly to exploit relations between filters at different layers as well as redundancy within the same layer. We show that we can achieve around 5x compression rate with small drop in accuracy on the KITTI driving dataset. We also show that masking can improve accuracy over the baseline with fewer parameters, even without enforcing compression loss.
As processing power has become more available, more human-like artificial intelligences are created to solve image processing tasks that we are inherently good at. As such we propose a model that estimates depth from a monocular image. Our approach utilizes a combination of structure from motion and stereo disparity. We estimate a pose between the source image and a different viewpoint and a dense depth map and use a simple transformation to reconstruct the image seen from said viewpoint. We can then use the real image at that viewpoint to act as supervision to train out model. The metric chosen for image comparison employs standard L1 and structural similarity and a consistency constraint between depth maps as well as smoothness constraint. We show that similar to human perception utilizing the correlation within the provided data by two different approaches increases the accuracy and outperforms the individual components.