For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially bootstrapped with supervised training on a labeled dataset and we look for a self-supervised training method that can subsequently improve the system over the supervised training baseline using only unlabeled data. In this work, we leverage temporal consistency between frames in monocular video to perform this bootstrapped self-supervised training. We show that a well-trained state-of-the-art semantic segmentation network can be further improved through our method. In addition, we show that the bootstrapped self-supervised training framework can help a network learn depth estimation better than pure supervised training or self-supervised training.
Handong Global University（韩东国际大学）；Sungkyunkwan University（成均馆大学）；Institute for Basic Science（基础科学研究院）
Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently …
Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent instance identifiers. We propose a novel solution with a multi-task network that performs monocular depth estimation and video panoptic segmentation. Since acquiring ground truth labels for both depth and image segmentation has a relatively large cost, we leverage the power of unlabeled video sequences with self-supervised monocular depth estimation and semi-supervised learnin…
In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where the instance ID encodes the depth ordering within image patches. To provide a coherent single explanation of an image we develop a Markov random field which takes as input the predictions of convolutional neural nets applied at overlapping patches of different resolutions, as well as the output of a connected component algorithm. It aims to pred…
The University of Adelaide（阿德莱德大学）；The University of Queensland（昆士兰大学）
Augmenting RGB data with measured depth has been shown to improve the performance of a range of tasks in computer vision including object detection and semantic segmentation. Although depth sensors such as the Microsoft Kinect have facilitated easy acquisition of such depth information, the vast majority of images used in vision tasks do not contain depth information. In this paper, we show that augmenting RGB images with estimated depth can also improve the accuracy of both object detection and semantic segmentation. Specifically, we first exploit the recent success of depth estimation from m…
Autonomous driving is a challenging topic that requires complex solutions in perception tasks such as recognition of road, lanes, traffic signs or lights, vehicles and pedestrians. Through years of research, computer vision has grown capable of tackling these tasks with monocular detectors that can provide remarkable detection rates with relatively low processing times. However, the recent appearance of Convolutional Neural Networks (CNNs) has revolutionized the computer vision field and has made possible approaches to perform full pixel-wise semantic segmentation in times close to real time (…
TRACE vzw（TRACE非营利组织）；KU Leuven（鲁汶大学）；ETHZ（苏黎世联邦理工学院）；Toyota Motor Europe（丰田汽车欧洲公司）
Monocular 3D object detection has recently shown promising results, however there remain challenging problems. One of those is the lack of invariance to different camera intrinsic parameters, which can be observed across different 3D object datasets. Little effort has been made to exploit the combination of heterogeneous 3D object datasets. In contrast to general intuition, we show that more data does not automatically guarantee a better performance, but rather, methods need to have a degree of 'camera independence' in order to benefit from large and heterogeneous training data. In this paper …
In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraints from semantic segmentation has been explored implicitly such as sharing and transforming features. In contrast, we propose to explicitly measure the border consistency between segmentation and depth and minimize it in a greedy manner by iteratively supervising the network towards a locally optimal solution. Partially this is motivated by our observation that semantic segme…
In this work, we present a fully self-supervised framework for semantic segmentation(FS^4). A fully bootstrapped strategy for semantic segmentation, which saves efforts for the huge amount of annotation, is crucial for building customized models from end-to-end for open-world domains. This application is eagerly needed in realistic scenarios. Even though recent self-supervised semantic segmentation methods have gained great progress, these works however heavily depend on the fully-supervised pretrained model and make it impossible a fully self-supervised pipeline. To solve this problem, we pro…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Vision Transformer (ViT) pretrained with a label-free self-supervised method, we successfully train a coarse image segmentation model for the Duckietown environment using 70 training images. Our model performs coarse image segmentation at the 8x8 patch level, and the inference resolution can be adjusted to balance prediction granularity and real-time perception constraints. We study how best to adapt a ViT to our task and environment, and find that some lightw…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT prediction targets; 2) target-aware decoder that tries to reduce the pressure on the encoder to memorize target-specific information in BERT pretraining. The first design is motivated by the observation that using a pretrained MAE to extract the features as the BERT prediction target for masked tokens can achieve better pretraining performance. Therefore, w…
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）
Monocular height estimation (MHE) from remote sensing imagery has high potential in generating 3D city models efficiently for a quick response to natural disasters. Most existing works pursue higher performance. However, there is little research exploring the interpretability of MHE networks. In this paper, we target at exploring how deep neural networks predict height from a single monocular image. Towards a comprehensive understanding of MHE networks, we propose to interpret them from multiple levels: 1) Neurons: unit-level dissection. Exploring the semantic and height selectivity of the lea…
The Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）；The Johns Hopkins University（约翰斯·霍普金斯大学）
An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images. For close-range vision tasks, height and orientation have been derived directly from stereo-computed depth and more recently from monocular depth predicted by deep networks. For long-range vision tasks such as Earth observation, depth cannot be reliably estimated with monocular images. Inspired by recent work in monocular height above ground prediction and optic…
Hazard detection and avoidance is a key technology for future robotic small body sample return and lander missions. Current state-of-the-practice methods rely on high-fidelity, a priori terrain maps, which require extensive human-in-the-loop verification and expensive reconnaissance campaigns to resolve mapping uncertainties. We propose a novel safety mapping paradigm that leverages deep semantic segmentation techniques to predict landing safety directly from a single monocular image, thus reducing reliance on high-fidelity, a priori data products. We demonstrate precise and accurate safety ma…
Objects may appear at arbitrary scales in perspective images of a scene, posing a challenge for recognition systems that process images at a fixed resolution. We propose a depth-aware gating module that adaptively selects the pooling field size in a convolutional network architecture according to the object scale (inversely proportional to the depth) so that small details are preserved for distant objects while larger receptive fields are used for those nearby. The depth gating signal is provided by stereo disparity or estimated directly from monocular input. We integrate this depth-aware gati…
Technical University of Munich（慕尼黑工业大学）；Artisense（Artisense公司）
The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a network architecture and training procedure for learning monocular 3D object detection without 3D bounding box labels. By representing the objects as triangular meshes and employing differentiable shape rendering, we define loss functions based on depth maps, segmentation masks, and ego- and object-motion, which are generated by pre-trained, off-the-shelf networks. We evaluate the proposed algorithm on the real-worl…
In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the point clouds from perspective image sequences while providing each point with instance-level semantic interpretations. Solving this problem requires the vision models to predict the spatial location, semantic class, and temporally consistent instance label for each 3D point. ViP-DeepLab approaches it by jointly performing monocular depth estimation and video panoptic segmentation. We name this joint task as Depth-awa…
Monocular camera sensors are vital to intelligent vehicle operation and automated driving assistance and are also heavily employed in traffic control infrastructure. Calibrating the monocular camera, though, is time-consuming and often requires significant manual intervention. In this work, we present an extrinsic camera calibration approach that automatizes the parameter estimation by utilizing semantic segmentation information from images and point clouds. Our approach relies on a coarse initial measurement of the camera pose and builds on lidar sensors mounted on a vehicle with high-precisi…
University of Adelaide（阿德莱德大学）；Queensland University of Technology（昆士兰科技大学）
Intra-operative automatic semantic segmentation of knee joint structures can assist surgeons during knee arthroscopy in terms of situational awareness. However, due to poor imaging conditions (e.g., low texture, overexposure, etc.), automatic semantic segmentation is a challenging scenario, which justifies the scarce literature on this topic. In this paper, we propose a novel self-supervised monocular depth estimation to regularise the training of the semantic segmentation in knee arthroscopy. To further regularise the depth estimation, we propose the use of clean training images captured by t…
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 propose a differentiable forward rigid projection module that plays a key role in our instance-wise depth and motion learning. Second, we design an instance-wise photometric and geometric consistency loss that effectively decomposes background and moving object regions. Lastly, we introduce a new auto-annotation scheme to produce video instance segmentation m…
We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement. Supervision is provided by a novel loss which measures the distance between this predicted flow subspace and an observed optical flow. This provides a new approach to learning scene representation tasks, such as monocular depth prediction or instance segmentation, in an unsupervised fashion using in-the-wild input videos without requiring camera poses, intrinsi…
Xiamen University（厦门大学）；Ningbo Boden AI Technology Co., Ltd.（宁波博登人工智能科技有限公司）
The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vulnerable to occluded and truncated objects. In this paper, a single-stage monocular 3D object detection model is proposed. An instance-segmentation head is integrated into the model training, which allows the model to be aware of the visible shape of a target object. The detection largely avoids interference from irrelevant regions surrounding the ta…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Inception Institute of Artificial Intelligence（启元人工智能研究院）；Meituan Group（美团集团）；Australian National University（澳大利亚国立大学）；Tencent（腾讯）；Beijing Institute of Technology（北京理工大学）
Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignore semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which ex…
KTH Royal Institute of Technology（瑞典皇家理工学院）；KU Leuven（鲁汶大学）
The state-of-the-art object detection and image classification methods can perform impressively on more than 9k and 10k classes, respectively. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This is not surprising when the restrictions caused by the lack of labeled data and high computation demand for segmentation are considered. In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead. In our embedding-based scalab…
Eindhoven University of Technology（埃因霍温理工大学）；Cyclomedia B.V（Cyclomedia公司）
Detection of buildings and other objects from aerial images has various applications in urban planning and map making. Automated building detection from aerial imagery is a challenging task, as it is prone to varying lighting conditions, shadows and occlusions. Convolutional Neural Networks (CNNs) are robust against some of these variations, although they fail to distinguish easy and difficult examples. We train a detection algorithm from RGB-D images to obtain a segmented mask by using the CNN architecture DenseNet.First, we improve the performance of the model by applying a statistical re-sa…
UMass Amherst（马萨诸塞大学阿默斯特分校）；University of Chicago（芝加哥大学）；TTI-Chicago（芝加哥丰田技术研究所）
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over time: as the agent moves, faraway mountains don't move much; nearby trees move a lot. This natural relationship between the appearance of objects and their motion is a rich source of information about the world. In this work, we start by training a deep network, using fully automatic supervision, to predict relative scene depth from single images. The relative d…
The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and trajectory tracking in a dense way. However, they lack flexibility of seamless switch between different scaled environments, i.e., indoor and outdoor scenes. In addition, semantic information are still hard to acquire in a 3D mapping. We address this challenge by combining the state-of-art deep learning method and semi-dense Simultaneous Localisation and Mapping (SL…
WildLIFT: Lifting monocular drone video to 3D for species-agnostic wildlife monitoring
Fondazione Bruno Kessler（布雷诺·科塞勒基金会）；University of Muenster（明斯特大学）；Max Planck Institute of Animal Behaviour（动物行为马克斯·普朗克研究所）；University of Konstanz（康斯坦茨大学）
In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results and a practical clustering technique to reject estimation outliers. In addition, we demonstrate a substantial performance boost achieved with a combination of multiple feature extractors. Furthermore, by using depth prediction with a deep neural network, we show that a significant amount of falsely matched keypoints are identified and eliminated. The proposed pipeline outperforms most of the existing approaches at th…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格普尔分校）
Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these approaches, they have not yet been exploited largely for solving the standard perception related problems encountered in autonomous navigation such as Visual Odometry (VO), Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM). This paper analyzes the problem of Monocular Visual Odometry using a Deep Learning-based framework, instead of the re…
School of Engineering, University of Kansas（堪萨斯大学工程学院）
In this paper, we proposed an end-to-end realtime global attention neural network (RGANet) for the challenging task of semantic segmentation. Different from the encoding strategy deployed by self-attention paradigms, the proposed global attention module encodes global attention via depth-wise convolution and affine transformations. The integration of these global attention modules into a hierarchy architecture maintains high inferential performance. In addition, an improved evaluation metric, namely MGRID, is proposed to alleviate the negative effect of non-convex, widely scattered ground-trut…
We present a novel embedding approach for video instance segmentation. Our method learns a spatio-temporal embedding integrating cues from appearance, motion, and geometry; a 3D causal convolutional network models motion, and a monocular self-supervised depth loss models geometry. In this embedding space, video-pixels of the same instance are clustered together while being separated from other instances, to naturally track instances over time without any complex post-processing. Our network runs in real-time as our architecture is entirely causal - we do not incorporate information from future…
Purdue University（普渡大学）；Curtin University（科廷大学）；University of Hawaii Cancer Center（夏威夷大学癌症中心）
We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting. Specifically, we are interested in end-to-end estimation of food portion size, which has great potential in the field of personal health management. Unlike image segmentation or object recognition where annotation can be obtained through large scale crowd sourcing, it is much more challenging to collect datasets for portion size estimation since human cannot accurately estimate the size of an object in an arbitrary 2D image …
Google Brain（谷歌大脑）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
Predicting the future to anticipate the outcome of events and actions is a critical attribute of autonomous agents; particularly for agents which must rely heavily on real time visual data for decision making. Working towards this capability, we address the task of predicting future frame segmentation from a stream of monocular video by leveraging the 3D structure of the scene. Our framework is based on learnable sub-modules capable of predicting pixel-wise scene semantic labels, depth, and camera ego-motion of adjacent frames. We further propose a recurrent neural network based model capable …
Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR)（德国航空航天中心遥感技术研究所（IMF））；Signal Processing in Earth Observation (SiPEO), Technical University of Munich (TUM)（慕尼黑工业大学地球观测信号处理研究所（SiPEO））
In this paper we tackle a very novel problem, namely height estimation from a single monocular remote sensing image, which is inherently ambiguous, and a technically ill-posed problem, with a large source of uncertainty coming from the overall scale. We propose a fully convolutional-deconvolutional network architecture being trained end-to-end, encompassing residual learning, to model the ambiguous mapping between monocular remote sensing images and height maps. Specifically, it is composed of two parts, i.e., convolutional sub-network and deconvolutional sub-network. The former corresponds to…
