Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
KAIST（韩国科学技术院）；DGIST（大邱庆北科学技术院）；Microsoft Research Asia（微软亚洲研究院）
Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon
备注：
Accepted to AAAI 2021. Code/dataset/models are available at https://github.com/SeokjuLee/Insta-DM. arXiv admin note: substantial text overlap with arXiv:1912.09351
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are available at https://github.com/SeokjuLee/Insta-DM .
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-s…
Google Research（谷歌研究院）；Robotics at Google（谷歌机器人）；Waymo LLC（Waymo有限责任公司）
We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy…
MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction
Columbia University（哥伦比亚大学）；Cloudspace Technology（云空间科技）；The University of Tokyo（东京大学）；Dianjing Ciyuan Culture（电境慈源文化）；Dalian University of Technology（大连理工大学）
German Research Center for Artificial Intelligence - DFKI（德国人工智能研究中心）；Birla Institute of Technology and Science - BITS Pilani（比尔拉技术与科学学院）；University of Applied Sciences Mannheim（曼海姆应用科学大学）；University of Kaiserslautern - TUK（凯泽斯劳滕大学）
Scene flow is the dense 3D reconstruction of motion and geometry of a scene. Most state-of-the-art methods use a pair of stereo images as input for full scene reconstruction. These methods depend a lot on the quality of the RGB images and perform poorly in regions with reflective objects, shadows, ill-conditioned light environment and so on. LiDAR measurements are much less sensitive to the aforementioned conditions but LiDAR features are in general unsuitable for matching tasks due to their sparse nature. Hence, using both LiDAR and RGB can potentially overcome the individual disadvantages of…
German Research Center for Artificial Intelligence – DFKI（德国人工智能研究中心–DFKI）；BMW Group（宝马集团）
Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular camera setup, i.e. using a single sensor. Towards this end, we exploit the latest achievements in single image depth estimation, optical flow, and sparse-to-dense interpolation and propose a monocular combination approach (MonoComb) to compute dense scene flow. MonoComb uses optical flow to relate reconstructed 3D positions over time and interpolates occluded areas. This way, existing monocular methods are outperforme…
Self-supervised monocular depth estimation approaches either ignore independently moving objects in the scene or need a separate segmentation step to identify them. We propose MonoDepthSeg to jointly estimate depth and segment moving objects from monocular video without using any ground-truth labels. We decompose the scene into a fixed number of components where each component corresponds to a region on the image with its own transformation matrix representing its motion. We estimate both the mask and the motion of each component efficiently with a shared encoder. We evaluate our method on thr…
Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the g…
University of California, San Diego（加利福尼亚大学圣地亚哥分校）
Real-scale scene flow estimation has become increasingly important for 3D computer vision. Some works successfully estimate real-scale 3D scene flow with LiDAR. However, these ubiquitous and expensive sensors are still unlikely to be equipped widely for real application. Other works use monocular images to estimate scene flow, but their scene flow estimations are normalized with scale ambiguity, where additional depth or point cloud ground truth are required to recover the real scale. Even though they perform well in 2D, these works do not provide accurate and reliable 3D estimates. We present…
ETH Zurich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）；KU Leuven（鲁汶大学）
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists little to no literature addressing the same for dynamic and deformable scenes. In this work, we present an unsupervised monocular framework for dense depth estimation of dynamic scenes, which jointly reconstructs rigid and non-rigid parts without explicitly modelling the camera motion. Using dense correspondences, we derive a training objective that aims to opportunistically pres…
We present a generalised self-supervised learning approach for monocular estimation of the real depth across scenes with diverse depth ranges from 1--100s of meters. Existing supervised methods for monocular depth estimation require accurate depth measurements for training. This limitation has led to the introduction of self-supervised methods that are trained on stereo image pairs with a fixed camera baseline to estimate disparity which is transformed to depth given known calibration. Self-supervised approaches have demonstrated impressive results but do not generalise to scenes with differen…
Technical University of Munich（慕尼黑工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid representing the scene; this feature grid is then decoded into an implicit 3D scene representation. Key to our approach is the transformer architecture that enables the network to learn to attend to the most relevant image frames for each 3D location in the scene, supervised only by the scene reconstruction task. Features are fused in a coarse-to-fine fashion, s…
Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on indoor environments with camera rotation. Indoor, rotated scenes are common for less constrained applications and pose problems for two reasons: abundance of low texture regions and increased complexity of depth cues for images under rotation. In an effort to extend self-supervised learning to more generalised environments we propose two additions. First, w…
Australian National University（澳大利亚国立大学）；Northwestern Polytechnical University（西北工业大学）；Australia Centre for Robotic Vision（澳大利亚机器人视觉中心）
This paper proposes a new approach for monocular dense 3D reconstruction of a complex dynamic scene from two perspective frames. By applying superpixel over-segmentation to the image, we model a generically dynamic (hence non-rigid) scene with a piecewise planar and rigid approximation. In this way, we reduce the dynamic reconstruction problem to a "3D jigsaw puzzle" problem which takes pieces from an unorganized "soup of superpixels". We show that our method provides an effective solution to the inherent relative scale ambiguity in structure-from-motion. Since our method does not assume a tem…
BNRist（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）；City University of Hong Kong（香港城市大学）；Tencent PCG（腾讯平台与内容事业群）
High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstruction approaches with neural implicit representations have shown a promising ability for complete scene reconstruction, while their results are often over-smooth and lack enough geometric details. This paper introduces a novel neural implicit scene representation with volume rendering for high-fidelity online 3D scene reconstruction from monocular videos. For fine-grained reconstruction, our key insight is to incorpo…
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 pr…
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based model capable of performing two tasks:- sparse depth completion (i.e. generating complete dense scene depth given a sparse depth image as the input) and monocular depth estimation (i.e. predicting scene depth from a single RGB image) via two sub-networks jointly trained end to end using data randomly sampled from a publicly available corpus of synthetic and re…
Most monocular depth sensing methods use conventionally captured images that are created without considering scene content. In contrast, animal eyes have fast mechanical motions, called saccades, that control how the scene is imaged by the fovea, where resolution is highest. In this paper, we present the SaccadeCam framework for adaptively distributing resolution onto regions of interest in the scene. Our algorithm for adaptive resolution is a self-supervised network and we demonstrate results for end-to-end learning for monocular depth estimation. We also show preliminary results with a real …
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
Institute for Photogrammetry and Geoinformatics, University of Stuttgart（摄影测量与地理信息学研究所，斯图加特大学）；Technical University of Munich（慕尼黑技术大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Robert Bosch GmbH（罗伯特·博世有限公司）；Goethe University（歌德大学）
In this paper we present mono-stixels, a compact environment representation specially designed for dynamic street scenes. Mono-stixels are a novel approach to estimate stixels from a monocular camera sequence instead of the traditionally used stereo depth measurements. Our approach jointly infers the depth, motion and semantic information of the dynamic scene as a 1D energy minimization problem based on optical flow estimates, pixel-wise semantic segmentation and camera motion. The optical flow of a stixel is described by a homography. By applying the mono-stixel model the degrees of freedom o…
Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
Institute of Medical Robotics and Department of Automation, Shanghai Jiao Tong University（上海交通大学医学机器人研究所和自动化系）；Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai（系统控制与信息处理重点实验室，教育部，上海）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）
ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）
Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of individuals and the 3D pose estimation by providing rich geometry features. Motivated by this, we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light. Specifically, we design an effective fusion strategy to take advantage of multi-modal input data, includ…
University of Kaiserslautern（凯泽斯劳滕大学）；DFKI（德国人工智能研究中心）
The paper introduces an accurate solution to dense orthographic Non-Rigid Structure from Motion (NRSfM) in scenarios with severe occlusions or, likewise, inaccurate correspondences. We integrate a shape prior term into variational optimisation framework. It allows to penalize irregularities of the time-varying structure on the per-pixel level if correspondence quality indicator such as an occlusion tensor is available. We make a realistic assumption that several non-occluded views of the scene are sufficient to estimate an initial shape prior, though the entire observed scene may exhibit non-r…
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model parameters. In this paper, an unsupervised learning framework is proposed to jointly predict monocular depth and complete 3D motion including the motions of moving objects and camera. (1) Recurrent modulation units are used to adaptively and iteratively fuse encoder and decoder features. This not only improves the single-image depth inference but also does not…
MPI for Informatics（马克斯·普朗克信息学研究所）；Facebook Reality Labs Research（Facebook现实实验室研究）
We present Non-Rigid Neural Radiance Fields (NR-NeRF), a reconstruction and novel view synthesis approach for general non-rigid dynamic scenes. Our approach takes RGB images of a dynamic scene as input (e.g., from a monocular video recording), and creates a high-quality space-time geometry and appearance representation. We show that a single handheld consumer-grade camera is sufficient to synthesize sophisticated renderings of a dynamic scene from novel virtual camera views, e.g. a `bullet-time' video effect. NR-NeRF disentangles the dynamic scene into a canonical volume and its deformation. S…
In this paper, we describe a method to capture nearly entirely spherical (360 degree) depth information using two adjacent frames from a single spherical video with motion parallax. After illustrating a spherical depth information retrieval using two spherical cameras, we demonstrate monocular spherical stereo by using stabilized first-person video footage. Experiments demonstrated that the depth information was retrieved on up to 97% of the entire sphere in solid angle. At a speed of 30 km/h, we were able to estimate the depth of an object located over 30 m from the camera. We also reconstruc…
Whole understanding of the surroundings is paramount to autonomous systems. Recent works have shown that deep neural networks can learn geometry (depth) and motion (optical flow) from a monocular video without any explicit supervision from ground truth annotations, particularly hard to source for these two tasks. In this paper, we take an additional step toward holistic scene understanding with monocular cameras by learning depth and motion alongside with semantics, with supervision for the latter provided by a pre-trained network distilling proxy ground truth images. We address the three task…
