We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a dataset and methods to tackle this dilemma, aiming to predict accurate depth up to an affine transformation with good generalization to diverse scenes. First we construct a large-scale and diverse dataset, termed Diverse Scene Depth dataset (DiverseDepth), which has a broad range of scenes and foreground contents. Compared with previous learning objectives, i.e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes. Furthermore, in order to train the model on the complex dataset effectively, we propose a multi-curriculum learning method. Experiments show that our method outperforms previous methods on 8 datasets by a large margin with the zero-shot test setting, demonstrating the excellent generalization capacity of the learned model to diverse scenes. The reconstructed point clouds with the predicted depth show that our method can recover high-quality 3D shapes. Code and dataset are available at: https://tinyurl.com/DiverseDepth
The University of Adelaide（阿德莱德大学）；Monash University（莫纳什大学）
Monocular depth prediction plays a crucial role in understanding 3D scene geometry. Although recent methods have achieved impressive progress in terms of evaluation metrics such as the pixel-wise relative error, most methods neglect the geometric constraints in the 3D space. In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, namely, virtual normal directions determined by randomly sampled three points in the reconstructed 3D space, we significantly improve the accuracy and r…
SZTAKI（匈牙利科学院计算机与自动化研究所）；University of Debrecen（德布勒森大学）；Czech Technical University in Prague（布拉格捷克理工大学）
We propose a new approach for combining deep-learned non-metric monocular depth with affine correspondences (ACs) to estimate the relative pose of two calibrated cameras from a single correspondence. Considering the depth information and affine features, two new constraints on the camera pose are derived. The proposed solver is usable within 1-point RANSAC approaches. Thus, the processing time of the robust estimation is linear in the number of correspondences and, therefore, orders of magnitude faster than by using traditional approaches. The proposed 1AC+D solver is tested both on synthetic …
The Midas Touch for Metric Depth: Interpretable Metricization for Generalizable Depth Perception
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海智能自主系统研究院）；College of Electronic & Information Engineering, Tongji University（同济大学电子与信息工程学院）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Institute of Intelligent Science and Technology（上海智能科学技术研究院）
In this paper, we address monocular depth estimation with deep neural networks. To enable training of deep monocular estimation models with various sources of datasets, state-of-the-art methods adopt image-level normalization strategies to generate affine-invariant depth representations. However, learning with image-level normalization mainly emphasizes the relations of pixel representations with the global statistic in the images, such as the structure of the scene, while the fine-grained depth difference may be overlooked. In this paper, we propose a novel multi-scale depth normalization met…
University of Bologna（博洛尼亚大学）；Oxford Internet Institute（牛津互联网研究院）；University of Surrey（萨里大学）；Hikvision Research Institute（海康威视研究院）；Megvii（旷视科技）；Insta360（影石创新）；Harbin Institute of Technology（哈尔滨工业大学）；University of Trento（特伦托大学）；University of Science, VNU-HCM（胡志明市越南科学大学）；University of Reading（雷丁大学）
Language as Prior, Vision as Calibration: Metric Scale Recovery for Monocular Depth Estimation
Hefei University of Technology, Hefei, Anhui, China（合肥工业大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, Anhui, China（人工智能研究所）；University of Science and Technology of China, Hefei, Anhui, China（中国科学技术大学）
VIMD: Monocular Visual-Inertial Motion and Depth Estimation
University of Delaware (UD) College of Engineering（德克萨斯大学达勒姆分校工程学院）；University of Delaware（德克萨斯大学达勒姆分校）；Robot Perception and Navigation Group (RPNG)（机器人感知与导航小组）
Carnegie Mellon University（卡内基梅隆大学）；Mila-University of Montreal（蒙特利尔大学米拉研究院）；Polytechnique Montreal（蒙特利尔综合理工大学）；Element AI（元素人工智能公司）
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manner, without using any form of ground-truth depth information. We show how it is possible to use these depths as intermediate computations within a new backpropable loss to predict the parameters of a 3D affine transformation matrix that maps inferred 3D keypoints of an input face …
Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology, China（北京智能信息科技重点实验室，计算机科学与技术学院，北京理工大学，中国）；Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University, China（广东机器感知与智能计算实验室，深圳MSU-BIT大学，中国）；NVIDIA
Czech Technical University in Prague（布拉格捷克理工大学）；HOVER Inc.（HOVER公司）
We consider the problem of two-view matching under significant viewpoint changes with view synthesis. We propose two novel methods, minimizing the view synthesis overhead. The first one, named DenseAffNet, uses dense affine shapes estimates from AffNet, which allows it to partition the image, rectifying each partition with just a single affine map. The second one, named DepthAffNet, combines information from depth maps and affine shapes estimates to produce different sets of rectifying affine maps for different image partitions. DenseAffNet is faster than the state-of-the-art and more accurate…
AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior
The Hong Kong University of Science & Technology（香港科技大学）；The University of Hong Kong（香港大学）；Southern University of Science & Technology（南方科技大学）；Zhejiang University（浙江大学）；LimX Dynamics
LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
Central South University（中南大学）；Nanjing University of Science and Technology（南京理工大学）；Sun Yat-sen University（中山大学）；Shandong Normal University（山东师范大学）；Qilu University of Technology（齐鲁工业大学）
Institute for Computer Graphics and Vision, Graz University of Technology（格拉茨技术大学计算机图形与视觉研究所）
In this work we present a novel approach for single depth map super-resolution. Modern consumer depth sensors, especially Time-of-Flight sensors, produce dense depth measurements, but are affected by noise and have a low lateral resolution. We propose a method that combines the benefits of recent advances in machine learning based single image super-resolution, i.e. deep convolutional networks, with a variational method to recover accurate high-resolution depth maps. In particular, we integrate a variational method that models the piecewise affine structures apparent in depth data via an aniso…
Despite the significant progress that depth-based 3D hand pose estimation methods have made in recent years, they still require a large amount of labeled training data to achieve high accuracy. However, collecting such data is both costly and time-consuming. To tackle this issue, we propose a semi-supervised method to significantly reduce the dependence on labeled training data. The proposed method consists of two identical networks trained jointly: a teacher network and a student network. The teacher network is trained using both the available labeled and unlabeled samples. It leverages the u…
