University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Google Research（谷歌研究院）
Antonio Loquercio, Alexey Dosovitskiy, Davide Scaramuzza
备注：
Accepted for Publication at the IEEE Robotics and Automation Letters (RA-L) 2020, and International Conference on Intelligent Robots and Systems (IROS) 2020
Motivated by the astonishing capabilities of natural intelligent agents and inspired by theories from psychology, this paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment. Existing works for depth estimation require either massive amounts of annotated training data or some form of hard-coded geometrical constraint. This paper explores a new approach to learning depth perception requiring neither of those. Specifically, we train a specialized global-local network architecture with what would be available to a robot interacting with the environment: from extremely sparse depth measurements down to even a single pixel per image. From a pair of consecutive images, our proposed network outputs a latent representation of the observer's motion between the images and a dense depth map. Experiments on several datasets show that, when ground truth is available even for just one of the image pixels, the proposed network can learn monocular dense depth estimation up to 22.5% more accurately than state-of-the-art approaches. We believe that this work, despite its scientific interest, lays the foundations to learn depth from extremely sparse supervision, which can be valuable to all robotic systems acting under severe bandwidth or sensing constraints.
Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Huawei European Research Center（华为欧洲研究中心）；Technische Universität München（慕尼黑工业大学）
Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is …
We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a camera's aperture as supervision. Prior works use a depth sensor's outputs or images of the same scene from alternate viewpoints as supervision, while our method instead uses images from the same viewpoint taken with a varying camera aperture. To enable learning algorithms to use aperture effects as supervision, we introduce two differentiable aperture rendering functions that use the input image and predicted depths to simulate the depth-of-field …
Hikvision Research Institute (HRI), Hangzhou Hikvision Digital Technology Co. Ltd（海康威视研究院（HRI），杭州海康威视数字技术有限公司）
This paper addresses the importance of full-image supervision for monocular depth estimation. We propose a semi-supervised architecture, which combines both unsupervised framework of using image consistency and supervised framework of dense depth completion. The latter provides full-image depth as supervision for the former. Ego-motion from navigation system is also embedded into the unsupervised framework as output supervision of an inner temporal transform network, making monocular depth estimation better. In the evaluation, we show that our proposed model outperforms other approaches on dep…
Renault Software Factory（雷诺软件工厂）；CNRS-I3S, Côte d’Azur University（法国国家科学研究中心I3S实验室，蔚蓝海岸大学）
This paper proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only 6-DOF camera motion but also 6-DOF moving object instances. Self-supervision is performed by warping the images across a video sequence using depth and scene motion including object instances. One novelty of the proposed method is the use of the multi-head attention of the transformer network that matches moving objects across time and models their interaction and dynamics. This enables accurate and robust pose estimation for each object …
Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室）
We consider the problem of dense depth prediction from a sparse set of depth measurements and a single RGB image. Since depth estimation from monocular images alone is inherently ambiguous and unreliable, to attain a higher level of robustness and accuracy, we introduce additional sparse depth samples, which are either acquired with a low-resolution depth sensor or computed via visual Simultaneous Localization and Mapping (SLAM) algorithms. We propose the use of a single deep regression network to learn directly from the RGB-D raw data, and explore the impact of number of depth samples on pred…
Renault Software Factory（雷诺软件工厂）；CNRS-I3S（法国国家科学研究中心I3S实验室）；Côte d’Azur University（蔚蓝海岸大学）
This paper addresses the problem of end-to-end self-supervised forecasting of depth and ego motion. Given a sequence of raw images, the aim is to forecast both the geometry and ego-motion using a self supervised photometric loss. The architecture is designed using both convolution and transformer modules. This leverages the benefits of both modules: Inductive bias of CNN, and the multi-head attention of transformers, thus enabling a rich spatio-temporal representation that enables accurate depth forecasting. Prior work attempts to solve this problem using multi-modal input/output with supervis…
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 estimati…
Recently, several works have proposed fusing radar data as an additional perceptual signal into monocular depth estimation models because radar data is robust against varying light and weather conditions. Although improved performances were reported in prior works, it is still hard to tell how much depth information radar can contribute to a depth estimation model. In this paper, we propose radar inference and supervision experiments to investigate the intrinsic depth potential of radar data using state-of-the-art depth estimation models on the nuScenes dataset. In the inference experiment, th…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates su…
Monocular depth estimation is an interesting and challenging problem as there is no analytic mapping known between an intensity image and its depth map. Recently there has been a lot of data accumulated through depth-sensing cameras, in parallel to that researchers started to tackle this task using various learning algorithms. In this paper, a deep sparse coding method is proposed for monocular depth estimation along with an approach for deterministic dictionary initialization.
We present a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels. The model works simultaneously for both indoor/outdoor scenes and produces state-of-the-art dense depth maps at nearly real-time speeds on both the NYUv2 and KITTI datasets. We surpass the state-of-the-art for monocular depth estimation even with depth values for only 1 out of every ~10000 image pixels, and we outperform other sparse-to-dense depth methods at all sparsity levels. With depth values for 1/256 of the image pixels, we achieve a mean absolute erro…
We present an approach to depth estimation that fuses information from a stereo pair with sparse range measurements derived from a LIDAR sensor or a range camera. The goal of this work is to exploit the complementary strengths of the two sensor modalities, the accurate but sparse range measurements and the ambiguous but dense stereo information. These two sources are effectively and efficiently fused by combining ideas from anisotropic diffusion and semi-global matching. We evaluate our approach on the KITTI 2015 and Middlebury 2014 datasets, using randomly sampled ground truth range measureme…
University of California, Irvine（加州大学欧文分校）；Trifo, Inc.（追觅科技（美国）有限公司）
In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the dimensional nature of depth images, our network offers a novel 3D-to-2D coarse-to-fine dual densification design that is both accurate and lightweight. Depth densification is first performed in 3D space via point cloud completion, followed by a specially designed encoder-decoder structure that utilizes the projected dense depth from 3D completion and the origi…
Valeo und Schalter und Sensoren GmbH（法雷奥开关与传感器有限公司）；Valeo Vision Systems（法雷奥视觉系统公司）；Technische University, Chemnitz（开姆尼茨工业大学）
Near field depth estimation around a self driving car is an important function that can be achieved by four wide angle fisheye cameras having a field of view of over 180. Depth estimation based on convolutional neural networks (CNNs) produce state of the art results, but progress is hindered because depth annotation cannot be obtained manually. Synthetic datasets are commonly used but they have limitations. For instance, they do not capture the extensive variability in the appearance of objects like vehicles present in real datasets. There is also a domain shift while performing inference on n…
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvement is limited due to its low density and imbalanced distribution. To maximize the utility from the sparse source, we propose $S^3$ technique, which expands the depth value from sparse cues while estimating the confidence of expanded region. The proposed $S^3$ can be applied to various guided depth estimation approaches and trained end-to-end at di…
We present a deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements, for instance from a lidar. While the lidar may provide a depth value for a small percentage of the pixels, we exploit regularities reflected in the training set to complete the map so as to have a probability over depth for each pixel in the image. We exploit a Conditional Prior Network, that allows associating a probability to each depth value given an image, and combine it with a likelihood term that uses the sparse measurements. Option…
We integrate sparse radar data into a monocular depth estimation model and introduce a novel preprocessing method for reducing the sparseness and limited field of view provided by radar. We explore the intrinsic error of different radar modalities and show our proposed method results in more data points with reduced error. We further propose a novel method for estimating dense depth maps from monocular 2D images and sparse radar measurements using deep learning based on the deep ordinal regression network by Fu et al. Radar data are integrated by first converting the sparse 2D points to a heig…
Helen Wills Neuroscience Institute, University of California, Berkeley（加州大学伯克利分校海伦·威尔斯神经科学研究所）；School of Optometry, University of California, Berkeley（加州大学伯克利分校视光学院）；Department of EECS, Computer Science Division, University of California, Berkeley（加州大学伯克利分校电气工程与计算机科学系计算机科学部）
This paper introduces a new method for learning and inferring sparse representations of depth (disparity) maps. The proposed algorithm relaxes the usual assumption of the stationary noise model in sparse coding. This enables learning from data corrupted with spatially varying noise or uncertainty, typically obtained by laser range scanners or structured light depth cameras. Sparse representations are learned from the Middlebury database disparity maps and then exploited in a two-layer graphical model for inferring depth from stereo, by including a sparsity prior on the learned features. Since …
Samsung Research UK（三星英国研究院）；Centre for Research and Technology Hellas (CERTH)（希腊研究与技术中心）；Information Technologies Institute（信息技术研究所）
Monocular (relative or metric) depth estimation is a critical task for various applications, such as autonomous vehicles, augmented reality and image editing. In recent years, with the increasing availability of mobile devices, accurate and mobile-friendly depth models have gained importance. Increasingly accurate models typically require more computational resources, which inhibits the use of such models on mobile devices. The mobile use case is arguably the most unrestricted one, which requires highly accurate yet mobile-friendly architectures. Therefore, we try to answer the following quest…
Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression problem, requiring annotated labels as supervision at training time, in the past few years a substantial amount of work has been done in self-supervised depth training based on strong geometric cues, both from stereo cameras and more recently from monocular video sequences. In this paper we investigate how these two approaches (supervised & self-supervised) can be effectively combined, so that a depth model can learn…
Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion
Dalian University of Technology（大连理工大学）；Beihang University（北京航空航天大学）；College of Computer Science and Engineering, Shandong University of Science and Technology（山东科技大学计算机科学与工程学院）
Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image (monodepth) with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Auxiliary Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion, depending on whether only RGB images or also sparse point clouds are available at inference time. First, we decouple the image and depth map encoding stages using spars…
Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss
School of Computer Science The University of Sydney Sydney, Australia；School of Computer Science University of Bristol Bristol, United Kingdom；School of Science Edith Cowan University Perth, Australia
Tsinghua University（清华大学）；Wayne State University（韦恩州立大学）
It is vital to infer signed distance functions (SDFs) from 3D point clouds. The latest methods rely on generalizing the priors learned from large scale supervision. However, the learned priors do not generalize well to various geometric variations that are unseen during training, especially for extremely sparse point clouds. To resolve this issue, we present a neural network to directly infer SDFs from single sparse point clouds without using signed distance supervision, learned priors or even normals. Our insight here is to learn surface parameterization and SDFs inference in an end-to-end ma…
National Tsin Hua University（国立清华大学）；NEC Labs America（NEC美国实验室）；National Chiao Tung University（国立交通大学）
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) an…
Monocular visual odometry approaches that purely rely on geometric cues are prone to scale drift and require sufficient motion parallax in successive frames for motion estimation and 3D reconstruction. In this paper, we propose to leverage deep monocular depth prediction to overcome limitations of geometry-based monocular visual odometry. To this end, we incorporate deep depth predictions into Direct Sparse Odometry (DSO) as direct virtual stereo measurements. For depth prediction, we design a novel deep network that refines predicted depth from a single image in a two-stage process. We train …
We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients. Our proposed approach is based around the idea that true depth edges are more sensitive than texture edges to local constraints, and so they can be reliably disambiguated through a bidirectional diffusion process. First, we use epipolar-plane images to estimate sub-pixel disparity at a sparse set of pixels. To find sparse points efficiently, we propose an entropy-based refinement approach to a line estimate from a limited set of oriented filter banks. Next, to estim…
This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications depend on the awareness of their surroundings, and use depth cues to reason and react accordingly. On the one hand, monocular depth prediction methods fail to generate absolute and precise depth maps. On the other hand, stereoscopic approaches are still significantly outperformed by LiDAR based approaches. The goal of the depth completion task is to generat…
Large Depth Completion Model from Sparse Observations
Zhejiang University（浙江大学）；Tongyi Lab, Alibaba Group（阿里云实验室）；Fudan University（复旦大学）；Ningbo Innovation Center, Zhejiang University（宁波创新中心，浙江大学）；NingboTech University（宁波科技学院）；Jinhua Institute of Zhejiang University（金华大学浙大研究院）
Technical University of Munich（慕尼黑工业大学）；Google Research（谷歌研究院）
Neural radiance fields (NeRF) encode a scene into a neural representation that enables photo-realistic rendering of novel views. However, a successful reconstruction from RGB images requires a large number of input views taken under static conditions - typically up to a few hundred images for room-size scenes. Our method aims to synthesize novel views of whole rooms from an order of magnitude fewer images. To this end, we leverage dense depth priors in order to constrain the NeRF optimization. First, we take advantage of the sparse depth data that is freely available from the structure from mo…
We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, depths, and weights with respect to the loss by differential splatting that models points as Gaussians with analytic transmittance. Further, we develop an efficient optimization routine that can simultaneously optimize the 50k+ points required for complex scene reconstruction. We validate our routine using ground truth data and show high reconstruction quality. Then, we apply this…
University of São Paulo（圣保罗大学）；Toyota Research Institute（丰田研究院）
This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the training labels, which guide the optimization process. For indoor scenes, structured-light-based depth sensors (e.g. Kinect) are able to provide dense, albeit short-range, depth maps. On the other hand, for outdoor scenes, LiDARs are considered the standard sensor, which comparatively provides much sparser measurements, especially in areas further away. Rather…
Clemson University（克莱姆森大学）；The City University of New York（纽约市立大学）；Carnegie Mellon University（卡内基梅隆大学）
Self-supervised monocular depth prediction provides a cost-effective solution to obtain the 3D location of each pixel. However, the existing approaches usually lead to unsatisfactory accuracy, which is critical for autonomous robots. In this paper, we propose FusionDepth, a novel two-stage network to advance the self-supervised monocular dense depth learning by leveraging low-cost sparse (e.g. 4-beam) LiDAR. Unlike the existing methods that use sparse LiDAR mainly in a manner of time-consuming iterative post-processing, our model fuses monocular image features and sparse LiDAR features to pred…
