Light field cameras record not only the spatial information of observed scenes but also the directions of all incoming light rays. The spatial and angular information implicitly contain geometrical characteristics such as multi-view or epipolar geometry, which can be exploited to improve the performance of depth estimation. An Epipolar Plane Image (EPI), the unique 2D spatial-angular slice of the light field, contains patterns of oriented lines. The slope of these lines is associated with the disparity. Benefiting from this property of EPIs, some representative methods estimate depth maps by analyzing the disparity of each line in EPIs. However, these methods often extract the optimal slope of the lines from EPIs while ignoring the relationship between neighboring pixels, which leads to inaccurate depth map predictions. Based on the observation that an oriented line and its neighboring pixels in an EPI share a similar linear structure, we propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical EPIs. Specifically, we present a new feature-extraction module, called Oriented Relation Module (ORM), that constructs the relationship between the line orientations. To facilitate training, we also propose a refocusing-based data augmentation method to obtain different slopes from EPIs of the same scene point. Extensive experiments verify the efficacy of learning relations and show that our approach is competitive to other state-of-the-art methods. The code and the trained models are available at https://github.com/lkyahpu/EPI_ORM.git.
Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses. We show that our methods improve performance when applied to a range of different predictor architectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization performance of a synthetically trained depth predictor when evaluated on real images.
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.
Deep learning techniques hold promise to develop dense topography reconstruction and pose estimation methods for endoscopic videos. However, currently available datasets do not support effective quantitative benchmarking. In this paper, we introduce a comprehensive endoscopic SLAM dataset consisting of 3D point cloud data for six porcine organs, capsule and standard endoscopy recordings as well as synthetically generated data. A Panda robotic arm, two commercially available capsule endoscopes, two conventional endoscopes with different camera properties, and two high precision 3D scanners were employed to collect data from 8 ex-vivo porcine gastrointestinal (GI)-tract organs. In total, 35 sub-datasets are provided with 6D pose ground truth for the ex-vivo part: 18 sub-dataset for colon, 12 sub-datasets for stomach and 5 sub-datasets for small intestine, while four of these contain polyp-mimicking elevations carried out by an expert gastroenterologist. Synthetic capsule endoscopy frames from GI-tract with both depth and pose annotations are included to facilitate the study of simulation-to-real transfer learning algorithms. Additionally, we propound Endo-SfMLearner, an unsupervised monocular depth and pose estimation method that combines residual networks with spatial attention module in order to dictate the network to focus on distinguishable and highly textured tissue regions. The proposed approach makes use of a brightness-aware photometric loss to improve the robustness under fast frame-to-frame illumination changes. To exemplify the use-case of the EndoSLAM dataset, the performance of Endo-SfMLearner is extensively compared with the state-of-the-art. The codes and the link for the dataset are publicly available at https://github.com/CapsuleEndoscope/EndoSLAM. A video demonstrating the experimental setup and procedure is accessible through https://www.youtube.com/watch?v=G_LCe0aWWdQ.
Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems. State-of-the-art stereo matching methods based on convolutional neural networks require intensive computations on GPUs and are difficult to deploy on embedded systems. In this paper, we propose a stereo matching method, called MTStereo 2.0, for limited-resource systems that require efficient and accurate depth estimation. It is based on a Max-tree hierarchical representation of image pairs, which we use to identify matching regions along image scan-lines. The method includes a cost function that considers similarity of region contextual information based on the Max-trees and a disparity border preserving cost aggregation approach. MTStereo 2.0 improves on its predecessor MTStereo 1.0 as it a) deploys a more robust cost function, b) performs more thorough detection of incorrect matches, c) computes disparity maps with pixel-level rather than node-level precision. MTStereo provides accurate sparse and semi-dense depth estimation and does not require intensive GPU computations like methods based on CNNs. Thus it can run on embedded and robotics devices with low-power requirements. We tested the proposed approach on several benchmark data sets, namely KITTI 2015, Driving, FlyingThings3D, Middlebury 2014, Monkaa and the TrimBot2020 garden data sets, and achieved competitive accuracy and efficiency. The code is available at https://github.com/rbrandt1/MaxTreeS.
Prior Networks are a recently developed class of models which yield interpretable measures of uncertainty and have been shown to outperform state-of-the-art ensemble approaches on a range of tasks. They can also be used to distill an ensemble of models via Ensemble Distribution Distillation (EnD$^2$), such that its accuracy, calibration and uncertainty estimates are retained within a single model. However, Prior Networks have so far been developed only for classification tasks. This work extends Prior Networks and EnD$^2$ to regression tasks by considering the Normal-Wishart distribution. The properties of Regression Prior Networks are demonstrated on synthetic data, selected UCI datasets and a monocular depth estimation task, where they yield performance competitive with ensemble approaches.
We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while preserving the rest of the scene. To understand the effect of targeted perturbations, we conduct experiments on state-of-the-art monocular depth prediction methods. Our experiments reveal vulnerabilities in monocular depth prediction networks, and shed light on the biases and context learned by them.
Depth perception is paramount to tackle real-world problems, ranging from autonomous driving to consumer applications. For the latter, depth estimation from a single image represents the most versatile solution, since a standard camera is available on almost any handheld device. Nonetheless, two main issues limit its practical deployment: i) the low reliability when deployed in-the-wild and ii) the demanding resource requirements to achieve real-time performance, often not compatible with such devices. Therefore, in this paper, we deeply investigate these issues showing how they are both addressable adopting appropriate network design and training strategies -- also outlining how to map the resulting networks on handheld devices to achieve real-time performance. Our thorough evaluation highlights the ability of such fast networks to generalize well to new environments, a crucial feature required to tackle the extremely varied contexts faced in real applications. Indeed, to further support this evidence, we report experimental results concerning real-time depth-aware augmented reality and image blurring with smartphones in-the-wild.
Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be consistent. We propose a broadly applicable and fully computational method for augmenting learning with Cross-Task Consistency. The proposed formulation is based on inference-path invariance over a graph of arbitrary tasks. We observe that learning with cross-task consistency leads to more accurate predictions and better generalization to out-of-distribution inputs. This framework also leads to an informative unsupervised quantity, called Consistency Energy, based on measuring the intrinsic consistency of the system. Consistency Energy correlates well with the supervised error (r=0.67), thus it can be employed as an unsupervised confidence metric as well as for detection of out-of-distribution inputs (ROC-AUC=0.95). The evaluations are performed on multiple datasets, including Taskonomy, Replica, CocoDoom, and ApolloScape, and they benchmark cross-task consistency versus various baselines including conventional multi-task learning, cycle consistency, and analytical consistency.
We propose a novel method for combining synthetic and real images when training networks to determine geometric information from a single image. We suggest a method for mapping both image types into a single, shared domain. This is connected to a primary network for end-to-end training. Ideally, this results in images from two domains that present shared information to the primary network. Our experiments demonstrate significant improvements over the state-of-the-art in two important domains, surface normal estimation of human faces and monocular depth estimation for outdoor scenes, both in an unsupervised setting.
Data-driven depth estimation methods struggle with the generalization outside their training scenes due to the immense variability of the real-world scenes. This problem can be partially addressed by utilising synthetically generated images, but closing the synthetic-real domain gap is far from trivial. In this paper, we tackle this issue by using domain invariant defocus blur as direct supervision. We leverage defocus cues by using a permutation invariant convolutional neural network that encourages the network to learn from the differences between images with a different point of focus. Our proposed network uses the defocus map as an intermediate supervisory signal. We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images. We evaluate our model on synthetic and real datasets, showing compelling generalization results and state-of-the-art depth prediction.
Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy for lower latency. We present Bi3D, a method that estimates depth via a series of binary classifications. Rather than testing if objects are at a particular depth $D$, as existing stereo methods do, it classifies them as being closer or farther than $D$. This property offers a powerful mechanism to balance accuracy and latency. Given a strict time budget, Bi3D can detect objects closer than a given distance in as little as a few milliseconds, or estimate depth with arbitrarily coarse quantization, with complexity linear with the number of quantization levels. Bi3D can also use the allotted quantization levels to get continuous depth, but in a specific depth range. For standard stereo (i.e., continuous depth on the whole range), our method is close to or on par with state-of-the-art, finely tuned stereo methods.
Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.
This paper introduces GIMP-ML v1.1, a set of Python plugins for the widely popular GNU Image Manipulation Program (GIMP). It enables the use of recent advances in computer vision to the conventional image editing pipeline. Applications from deep learning such as monocular depth estimation, semantic segmentation, mask generative adversarial networks, image super-resolution, de-noising, de-hazing, matting, enlightening and coloring have been incorporated with GIMP through Python-based plugins. Additionally, operations on images such as k-means based color clustering have also been added. GIMP-ML relies on standard Python packages such as numpy, pytorch, open-cv, scipy. Apart from these, several image manipulation techniques using these plugins have been compiled and demonstrated in the YouTube channel (https://youtube.com/user/kritiksoman) with the objective of demonstrating the use-cases for machine learning based image modification. In addition, GIMP-ML also aims to bring the benefits of using deep learning networks used for computer vision tasks to routine image processing workflows. The code and installation procedure for configuring these plugins is available at https://github.com/kritiksoman/GIMP-ML.
In recent years, self-supervised methods for monocular depth estimation has rapidly become an significant branch of depth estimation task, especially for autonomous driving applications. Despite the high overall precision achieved, current methods still suffer from a) imprecise object-level depth inference and b) uncertain scale factor. The former problem would cause texture copy or provide inaccurate object boundary, and the latter would require current methods to have an additional sensor like LiDAR to provide depth ground-truth or stereo camera as additional training inputs, which makes them difficult to implement. In this work, we propose to address these two problems together by introducing DNet. Our contributions are twofold: a) a novel dense connected prediction (DCP) layer is proposed to provide better object-level depth estimation and b) specifically for autonomous driving scenarios, dense geometrical constrains (DGC) is introduced so that precise scale factor can be recovered without additional cost for autonomous vehicles. Extensive experiments have been conducted and, both DCP layer and DGC module are proved to be effectively solving the aforementioned problems respectively. Thanks to DCP layer, object boundary can now be better distinguished in the depth map and the depth is more continues on object level. It is also demonstrated that the performance of using DGC to perform scale recovery is comparable to that using ground-truth information, when the camera height is given and the ground point takes up more than 1.03\% of the pixels. Code is available at https://github.com/TJ-IPLab/DNet.
Scene flow estimation has been receiving increasing attention for 3D environment perception. Monocular scene flow estimation -- obtaining 3D structure and 3D motion from two temporally consecutive images -- is a highly ill-posed problem, and practical solutions are lacking to date. We propose a novel monocular scene flow method that yields competitive accuracy and real-time performance. By taking an inverse problem view, we design a single convolutional neural network (CNN) that successfully estimates depth and 3D motion simultaneously from a classical optical flow cost volume. We adopt self-supervised learning with 3D loss functions and occlusion reasoning to leverage unlabeled data. We validate our design choices, including the proxy loss and augmentation setup. Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks. Semi-supervised fine-tuning further improves the accuracy and yields promising results in real-time.
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. However, so far these two networks have to be trained separately. In this paper, we introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end. The resulting framework is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks -- yielding the highest entry on the KITTI image-based 3D object detection leaderboard at the time of submission. Our code will be made available at https://github.com/mileyan/pseudo-LiDAR_e2e.
Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV). Experiments on two popular indoor datasets, namely NYU-Depth-v2 and ScanNet, show that our method achieves state-of-the-art depth estimation results while using only a fraction of the number of parameters needed by the competing methods.
In this work, we tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning. Most existing methods assume that a consistent scale of depth and pose can be learned across all input samples, which makes the learning problem harder, resulting in degraded performance and limited generalization in indoor environments and long-sequence visual odometry application. To address this issue, we propose a novel system that explicitly disentangles scale from the network estimation. Instead of relying on PoseNet architecture, our method recovers relative pose by directly solving fundamental matrix from dense optical flow correspondence and makes use of a two-view triangulation module to recover an up-to-scale 3D structure. Then, we align the scale of the depth prediction with the triangulated point cloud and use the transformed depth map for depth error computation and dense reprojection check. Our whole system can be jointly trained end-to-end. Extensive experiments show that our system not only reaches state-of-the-art performance on KITTI depth and flow estimation, but also significantly improves the generalization ability of existing self-supervised depth-pose learning methods under a variety of challenging scenarios, and achieves state-of-the-art results among self-supervised learning-based methods on KITTI Odometry and NYUv2 dataset. Furthermore, we present some interesting findings on the limitation of PoseNet-based relative pose estimation methods in terms of generalization ability. Code is available at https://github.com/B1ueber2y/TrianFlow.