计算机视觉中的运动恢复结构（Structure from Motion, SfM）挑战，是指从一组由不同视角拍摄的2D图像计算出的投影测量序列中恢复场景3D结构的过程。SfM包含三个主要步骤：特征检测与匹配、相机运动估计，以及从估计的内外参数和特征中恢复3D结构。SfM中遇到的一个问题是，缺乏纹理或具有重复特征的场景会导致帧间特征匹配错误。语义分割提供了一条途径，通过使用深度卷积神经网络对输入图像中的像素进行标记，来验证和校正SfM模型。可以利用场景中各类别相关的语义和几何属性，为每一类对象应用先验约束。研究中使用了SfM流水线COLMAP和语义分割流水线DeepLab。结合稠密模型的平面重建，这些工具被用于确定可能从计算出的相机位置被遮挡的错误点，这是在给定语义标签以及重建平面的先验约束下进行的。在此，语义分割被集成到SfM中，在给定2D输入图像中对象检测结果的情况下，对3D点云应用先验。此外，比较了匹配关键点的语义标签，并丢弃语义标记不一致的点。进一步地，利用输入图像上的语义标签，在输出SfM模型中移除与运动相关的对象。所提出的方法在包含1102张重复建筑场景图像的数据集上进行了评估。该项目提供了一种改进3D SfM模型验证的新方法。
英文摘要：
The Structure from Motion (SfM) challenge in computer vision is the process of recovering the 3D structure of a scene from a series of projective measurements that are calculated from a collection of 2D images, taken from different perspectives. SfM consists of three main steps; feature detection and matching, camera motion estimation, and recovery of 3D structure from estimated intrinsic and extrinsic parameters and features.
A problem encountered in SfM is that scenes lacking texture or with repetitive features can cause erroneous feature matching between frames. Semantic segmentation offers a route to validate and correct SfM models by labelling pixels in the input images with the use of a deep convolutional neural network. The semantic and geometric properties associated with classes in the scene can be taken advantage of to apply prior constraints to each class of object. The SfM pipeline COLMAP and semantic segmentation pipeline DeepLab were used. This, along with planar reconstruction of the dense model, were used to determine erroneous points that may be occluded from the calculated camera position, given the semantic label, and thus prior constraint of the reconstructed plane. Herein, semantic segmentation is integrated into SfM to apply priors on the 3D point cloud, given the object detection in the 2D input images. Additionally, the semantic labels of matched keypoints are compared and inconsistent semantically labelled points discarded. Furthermore, semantic labels on input images are used for the removal of objects associated with motion in the output SfM models. The proposed approach is evaluated on a data-set of 1102 images of a repetitive architecture scene. This project offers a novel method for improved validation of 3D SfM models.
Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）；Volkswagen Group Automation（大众汽车集团自动化公司）
Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness. We propose to validate machine learning models for self-driving vehicles not only with given ground truth labels, but also with additional a-priori knowledge. In particular, we suggest to validate the drivable area in semantic segmentation masks using given street map data. We present first results, which indicate that prediction errors can be uncovered by map-based validation.
Moving objects in scenes are still a severe challenge for the SLAM system. Many efforts have tried to remove the motion regions in the images by detecting moving objects. In this way, the keypoints belonging to motion regions will be ignored in the later calculations. In this paper, we proposed a novel motion removal method, leveraging semantic information and optical flow to extract motion regions. Different from previous works, we don't predict moving objects or motion regions directly from image sequences. We computed rigid optical flow, synthesized by the depth and pose, and compared it ag…
University of Zagreb, Faculty of Electrical Engineering and Computing（萨格勒布大学电气工程与计算学院）；Rimac Automobili（里马茨汽车公司）
Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach consists of two modules. Feature-to-motion (F2M) module forecasts a dense deformation field that warps past features into their future positions. Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery. The compound F2MF model decouples the effects of motion from the effects of novelty in a ta…
Inria（法国国家信息与自动化研究所）；Laboratoire Jean Kuntzmann（让·昆茨曼实验室）
Fully convolutional neural networks (FCNNs) trained on a large number of images with strong pixel-level annotations have become the new state of the art for the semantic segmentation task. While there have been recent attempts to learn FCNNs from image-level weak annotations, they need additional constraints, such as the size of an object, to obtain reasonable performance. To address this issue, we present motion-CNN (M-CNN), a novel FCNN framework which incorporates motion cues and is learned from video-level weak annotations. Our learning scheme to train the network uses motion segments as s…
Object tracking is the cornerstone of many visual analytics systems. While considerable progress has been made in this area in recent years, robust, efficient, and accurate tracking in real-world video remains a challenge. In this paper, we present a hybrid tracker that leverages motion information from the compressed video stream and a general-purpose semantic object detector acting on decoded frames to construct a fast and efficient tracking engine. The proposed approach is compared with several well-known recent trackers on the OTB tracking dataset. The results indicate advantages of the pr…
Brown University（布朗大学）；NVIDIA（英伟达）；UC Irvine（加州大学欧文分校）
Given two consecutive frames from a pair of stereo cameras, 3D scene flow methods simultaneously estimate the 3D geometry and motion of the observed scene. Many existing approaches use superpixels for regularization, but may predict inconsistent shapes and motions inside rigidly moving objects. We instead assume that scenes consist of foreground objects rigidly moving in front of a static background, and use semantic cues to produce pixel-accurate scene flow estimates. Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo …
Hanbat National University（韩bat国立大学）；KAIST（韩国科学技术院）；SI Analytics Inc（SI分析公司）
Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labeling pixels having high confidences for unlabeled images. However, using only highconfidence pixels for self-training may result in losing much of the information in the unlabeled datasets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-adaptive semisupervision framework for semi-supervised semant…
Here, we present an end-to-end method to create 2D animation for a goalkeeper attempting to block a penalty kick, and then correct that motion using an iterative nonlinear optimization scheme. The input is a raw video that is fed into pose and object detection networks to find the skeleton of the goalkeeper and the ball. The output is a set of key frames of the skeleton associated with the corrected motion so that if the goalkeeper missed the ball, the animation will show then successfully deflecting it. Our method is robust enough correct different kinds of mistakes the goalkeeper can make, s…
German Research Center for Artificial Intelligence (DFKI) Saarbrücken（德国人工智能研究中心（DFKI）萨尔布吕肯）；Saarland University（萨尔大学）；Max-Planck Institute for Informatics（马克斯-普朗克计算机科学研究所）
Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a sem…
DFKI Saarbrücken（德国人工智能研究中心萨尔布吕肯）；Saarland University（萨尔兰大学）；Max-Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation…
Hamlyn Centre for Robotic Surgery（哈姆林机器人手术中心）；Imperial College London（伦敦帝国理工学院）
2D biomedical semantic segmentation is important for robotic vision in surgery. Segmentation methods based on Deep Convolutional Neural Network (DCNN) can out-perform conventional methods in terms of both accuracy and levels of automation. One common issue in training a DCNN for biomedical semantic segmentation is the internal covariate shift where the training of convolutional kernels is encumbered by the distribution change of input features, hence both the training speed and performance are decreased. Batch Normalization (BN) is the first proposed method for addressing internal covariate sh…
Technische Universität Dresden（德累斯顿工业大学）；Zhejiang University（浙江大学）
Structures suffer from the emergence of cracks, therefore, crack detection is always an issue with much concern in structural health monitoring. Along with the rapid progress of deep learning technology, image semantic segmentation, an active research field, offers another solution, which is more effective and intelligent, to crack detection Through numerous artificial neural networks have been developed to address the preceding issue, corresponding explorations are never stopped improving the quality of crack detection. This paper presents a novel artificial neural network architecture named …
Fraunhofer Center for Machine Learning, Fraunhofer IAIS（弗劳恩霍夫机器学习中心，弗劳恩霍夫智能分析与信息系统研究所）；Volkswagen Group Automation（大众集团自动化）
Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness, which motivates the thorough validation of learned models. However, current validation approaches mostly require ground truth data and are thus both cost-intensive and limited in their applicability. We propose to overcome these limitations by a model agnostic validation using a-priori knowledge from street maps. In particular, we show how to validate semantic segmentation masks and demonstrate the potential of our approach using OpenStreetMap. We introduce validation metrics that indicate fa…
Google Brain（谷歌大脑）；Harvard University（哈佛大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
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.
University of Freiburg（弗莱堡大学）；University of Technology, Nuremberg（纽伦堡工业大学）
In this paper we propose USegScene, a framework for semantically guided unsupervised learning of depth, optical flow and ego-motion estimation for stereo camera images using convolutional neural networks. Our framework leverages semantic information for improved regularization of depth and optical flow maps, multimodal fusion and occlusion filling considering dynamic rigid object motions as independent SE(3) transformations. Furthermore, complementary to pure photo-metric matching, we propose matching of semantic features, pixel-wise classes and object instance borders between the consecutive …
Universidade Estadual do Norte Fluminense（北弗鲁米嫩塞州立大学）；Laboratório de Instrumentação Nuclear EE/COPPE/UFRJ（里约热内卢联邦大学核仪器实验室）
The computation of 2-D optical flow by means of regularized pel-recursive algorithms raises a host of issues, which include the treatment of outliers, motion discontinuities and occlusion among other problems. We propose a new approach which allows us to deal with these issues within a common framework. Our approach is based on the use of a technique called Generalized Cross-Validation to estimate the best regularization scheme for a given pixel. In our model, the regularization parameter is a matrix whose entries can account for diverse sources of error. The estimation of the motion vectors t…
University of Michigan（密歇根大学）；Applied Research Associates（应用研究协会）；US Army DEVCOM Ground Vehicle Systems Center（美国陆军作战能力发展司令部地面车辆系统中心）
This work addresses a gap in semantic scene completion (SSC) data by creating a novel outdoor data set with accurate and complete dynamic scenes. Our data set is formed from randomly sampled views of the world at each time step, which supervises generalizability to complete scenes without occlusions or traces. We create SSC baselines from state-of-the-art open source networks and construct a benchmark real-time dense local semantic mapping algorithm, MotionSC, by leveraging recent 3D deep learning architectures to enhance SSC with temporal information. Our network shows that the proposed data …
Robotics Research Center（机器人研究中心）；IIIT Hyderabad（海得拉巴国际信息技术学院）
While the literature has been fairly dense in the areas of scene understanding and semantic labeling there have been few works that make use of motion cues to embellish semantic performance and vice versa. In this paper, we address the problem of semantic motion segmentation, and show how semantic and motion priors augments performance. We pro- pose an algorithm that jointly infers the semantic class and motion labels of an object. Integrating semantic, geometric and optical ow based constraints into a dense CRF-model we infer both the object class as well as motion class, for each pixel. We f…
International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）；Max Planck Institute For Intelligent Systems（马克斯·普朗克智能系统研究所）
Dynamic scene understanding is a challenging problem and motion segmentation plays a crucial role in solving it. Incorporating semantics and motion enhances the overall perception of the dynamic scene. For applications of outdoor robotic navigation, joint learning methods have not been extensively used for extracting spatio-temporal features or adding different priors into the formulation. The task becomes even more challenging without stereo information being incorporated. This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocula…
We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos in this paper. Recent unsupervised learning methods employ photometric errors between synthetic view and actual image as a supervision signal for training. In our method, we exploit semantic segmentation information to mitigate the effects of dynamic objects and occlusions in the scene, and to improve depth prediction performance by considering the correlation between depth and semantics. To avoid costly labeling process, we use noisy semantic segmentation results obtained by …
MOSA: Motion-Guided Semantic Alignment for Dynamic Scene Graph Generation
School of Computer Science and Technology, East China Normal University, Shanghai, China（东华大学计算机科学与技术学院）；School of Data Science and Engineering, East China Normal University, Shanghai, China（东华大学数据科学与工程学院）
Xiamen University（厦门大学）；PKU-Wuhan Institute for Artificial Intelligence（北京大学武汉人工智能研究院）
Video anomaly detection is an essential but challenging task. The prevalent methods mainly investigate the reconstruction difference between normal and abnormal patterns but ignore the semantics consistency between appearance and motion information of behavior patterns, making the results highly dependent on the local context of frame sequences and lacking the understanding of behavior semantics. To address this issue, we propose a framework of Appearance-Motion Semantics Representation Consistency that uses the gap of appearance and motion semantic representation consistency between normal an…
Xiamen University（厦门大学）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗克库尔分部）；Tibet University（西藏大学）；Wright State University（莱特州立大学）
Video anomaly detection refers to the identification of events that deviate from the expected behavior. Due to the lack of anomalous samples in training, video anomaly detection becomes a very challenging task. Existing methods almost follow a reconstruction or future frame prediction mode. However, these methods ignore the consistency between appearance and motion information of samples, which limits their anomaly detection performance. Anomalies only occur in the moving foreground of surveillance videos, so the semantics expressed by video frame sequences and optical flow without background …
SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
The University of Hong Kong（香港大学）；Ant Group（蚂蚁集团）；Tongyi（通义）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Huazhong University of Science and Technology（华中科技大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responses
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统全国重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；ZKTeco Co., Ltd.（熵基科技股份有限公司）
A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contact-missing. Driven by o…
Hong Kong University of Science and Technology（香港科技大学）
We propose a stereo vision-based approach for tracking the camera ego-motion and 3D semantic objects in dynamic autonomous driving scenarios. Instead of directly regressing the 3D bounding box using end-to-end approaches, we propose to use the easy-to-labeled 2D detection and discrete viewpoint classification together with a light-weight semantic inference method to obtain rough 3D object measurements. Based on the object-aware-aided camera pose tracking which is robust in dynamic environments, in combination with our novel dynamic object bundle adjustment (BA) approach to fuse temporal sparse…
