MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion
Hong Kong University of Science and Technology（香港科技大学）
Weihao Yuan, Rui Fan, Michael Yu Wang, Qifeng Chen
备注：
IEEE International Conference on Robotics and Automation (ICRA) + IEEE Robotics and Automation Letters (RA-L). arXiv admin note: substantial text overlap with arXiv:2001.08212
We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion of a camera to capture a sequence of images in horizontally or vertically aligned positions with the same parallax. In this system, we propose a new heuristic method and a robust learning-based method to fuse multiple cost volumes between the reference image and its surrounding images. To obtain training data, we build a synthetic dataset with multiscopic images. The experiments on the real-world Middlebury dataset and real robot demonstration show that our multiscopic vision system outperforms traditional two-frame stereo matching methods in depth estimation. Our code and dataset are available at https://sites.google.com/view/multiscopic.
The best way to combine the results of deep learning with standard 3D reconstruction pipelines remains an open problem. While systems that pass the output of traditional multi-view stereo approaches to a network for regularisation or refinement currently seem to get the best results, it may be preferable to treat deep neural networks as separate components whose results can be probabilistically fused into geometry-based systems. Unfortunately, the error models required to do this type of fusion are not well understood, with many different approaches being put forward. Recently, a few systems h…
ETH Zurich（苏黎世联邦理工学院）；Czech Technical University in Prague（布拉格捷克理工大学）；Microsoft（微软）
Volumetric depth map fusion based on truncated signed distance functions has become a standard method and is used in many 3D reconstruction pipelines. In this paper, we are generalizing this classic method in multiple ways: 1) Semantics: Semantic information enriches the scene representation and is incorporated into the fusion process. 2) Multi-Sensor: Depth information can originate from different sensors or algorithms with very different noise and outlier statistics which are considered during data fusion. 3) Scene denoising and completion: Sensors can fail to recover depth for certain mater…
The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable. To this end, we present a novel real-time capable machine learning-based method for depth map fusion. Similar to the seminal depth map fusion approach by Curless and Levoy, we only update a local group of voxels to ensure real-time capability. Instead of a simple linear fusion of depth information, we propose a neural network that predicts non-linear updates to better account for typical fusio…
Indian Institute Of Technology Madras（印度理工学院马德拉斯分校）
With an unprecedented increase in the number of agents and systems that aim to navigate the real world using visual cues and the rising impetus for 3D Vision Models, the importance of depth estimation is hard to understate. While supervised methods remain the gold standard in the domain, the copious amount of paired stereo data required to train such models makes them impractical. Most State of the Art (SOTA) works in the self-supervised and unsupervised domain employ a ResNet-based encoder architecture to predict disparity maps from a given input image which are eventually used alongside a ca…
Australian Centre for Robotic Vision at Queensland University of Technology (QUT)（昆士兰科技大学澳大利亚机器人视觉中心）
Learning-based approaches often outperform hand-coded algorithmic solutions for many problems in robotics. However, learning long-horizon tasks on real robot hardware can be intractable, and transferring a learned policy from simulation to reality is still extremely challenging. We present a novel approach to model-free reinforcement learning that can leverage existing sub-optimal solutions as an algorithmic prior during training and deployment. During training, our gated fusion approach enables the prior to guide the initial stages of exploration, increasing sample-efficiency and enabling lea…
A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Tsinghua University（清华大学）；Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术和图像处理研究所）
University of South Florida（南佛罗里达大学）；Federal University of Bahia（巴伊亚联邦大学）
We present an unconstrained ear recognition framework that outperforms state-of-the-art systems in different publicly available image databases. To this end, we developed CNN-based solutions for ear normalization and description, we used well-known handcrafted descriptors, and we fused learned and handcrafted features to improve recognition. We designed a two-stage landmark detector that successfully worked under untrained scenarios. We used the results generated to perform a geometric image normalization that boosted the performance of all evaluated descriptors. Our CNN descriptor outperforme…
University of Vigo（维戈大学）；University of Alicante（阿利坎特大学）；University of Granada（格拉纳达大学）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）
It is widely known that very small datasets produce overfitting in Deep Neural Networks (DNNs), i.e., the network becomes highly biased to the data it has been trained on. This issue is often alleviated using transfer learning, regularization techniques and/or data augmentation. This work presents a new approach, independent but complementary to the previous mentioned techniques, for improving the generalization of DNNs on very small datasets in which the involved classes share many visual features. The proposed methodology, called FuCiTNet (Fusion Class inherent Transformations Network), insp…
Peking University（北京大学）；Deepwise AI Lab（深睿医疗人工智能实验室）；Microsoft Research Asia（微软亚洲研究院）
Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts (1) a gen…
Learned pointcloud representations do not generalize well with an increase in distance to the sensor. For example, at a range greater than 60 meters, the sparsity of lidar pointclouds reaches to a point where even humans cannot discern object shapes from each other. However, this distance should not be considered very far for fast-moving vehicles: A vehicle can traverse 60 meters under two seconds while moving at 70 mph. For safe and robust driving automation, acute 3D object detection at these ranges is indispensable. Against this backdrop, we introduce faraway-frustum: a novel fusion strateg…
Sun Yat-Sen University（中山大学）；Xidian University（西安电子科技大学）；Northwestern Polytechnical University（西北工业大学）
Existing deep learning methods for action recognition in videos require a large number of labeled videos for training, which is labor-intensive and time-consuming. For the same action, the knowledge learned from different media types, e.g., videos and images, may be related and complementary. However, due to the domain shifts and heterogeneous feature representations between videos and images, the performance of classifiers trained on images may be dramatically degraded when directly deployed to videos. In this paper, we propose a novel method, named Deep Image-to-Video Adaptation and Fusion N…
Image fusion is a significant problem in many fields including digital photography, computational imaging and remote sensing, to name but a few. Recently, deep learning has emerged as an important tool for image fusion. This paper presents three deep convolutional sparse coding (CSC) networks for three kinds of image fusion tasks (i.e., infrared and visible image fusion, multi-exposure image fusion, and multi-modal image fusion). The CSC model and the iterative shrinkage and thresholding algorithm are generalized into dictionary convolution units. As a result, all hyper-parameters are learned …
Current RGB-based 6D object pose estimation methods have achieved noticeable performance on datasets and real world applications. However, predicting 6D pose from single 2D image features is susceptible to disturbance from changing of environment and textureless or resemblant object surfaces. Hence, RGB-based methods generally achieve less competitive results than RGBD-based methods, which deploy both image features and 3D structure features. To narrow down this performance gap, this paper proposes a framework for 6D object pose estimation that learns implicit 3D information from 2 RGB images.…
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
Tsinghua University（清华大学）；University of California, Berkeley（加州大学伯克利分校）；Massachusetts Institute of Technology（麻省理工学院）；Shanghai Qi Zhi Institute（上海期智研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
In the field of spatial-spectral fusion, the model-based method and the deep learning (DL)-based method are state-of-the-art. This paper presents a fusion method that incorporates the deep neural network into the model-based method for the most common case in the spatial-spectral fusion: PAN/multispectral (MS) fusion. Specifically, we first map the gradient of the high spatial resolution panchromatic image (HR-PAN) and the low spatial resolution multispectral image (LR-MS) to the gradient of the high spatial resolution multispectral image (HR-MS) via a deep residual convolutional neural networ…
Xi’an Jiaotong University（西安交通大学）；National Engineering Laboratory for Big Data Algorithm and Analysis Technology（大数据算法与分析技术国家工程实验室）；Shanghai Jiaotong University（上海交通大学）
Multi-atlas segmentation approach is one of the most widely-used image segmentation techniques in biomedical applications. There are two major challenges in this category of methods, i.e., atlas selection and label fusion. In this paper, we propose a novel multi-atlas segmentation method that formulates multi-atlas segmentation in a deep learning framework for better solving these challenges. The proposed method, dubbed deep fusion net (DFN), is a deep architecture that integrates a feature extraction subnet and a non-local patch-based label fusion (NL-PLF) subnet in a single network. The netw…
University of Washington（华盛顿大学）；Cornell University（康奈尔大学）；NVIDIA（英伟达）
Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a summary representation of the entire scene, even if most of the input is irrelevant to the agent's current goal. In this work, we flip this paradigm, by introducing EarlyFusion vision models that condition on a goal to build custom representations for downstream tasks. We show that these goal specific representations can be learned more quickly, are substantiall…
We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned feature representation for the fusion. The key idea is a separation between the scene representation used for the fusion and the output scene representation, via an additional translator network. Our neural network architecture consists of two main parts: a depth and feature fusion sub-network, which is followed by a translator sub-network to produce the fin…
This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data. Firstly, we transform the depth data into Sequential Front view Images(SFI) and fine-tune the pre-trained AlexNet on these images. Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images. Finally, learned features are extracted from both CNN, fused together to make a shared feature layer, and these features are fed to the classifier. We experiment with two classifiers, namely Support Vector Machin…
Traditional visual place recognition (VPR), usually using standard cameras, is easy to fail due to glare or high-speed motion. By contrast, event cameras have the advantages of low latency, high temporal resolution, and high dynamic range, which can deal with the above issues. Nevertheless, event cameras are prone to failure in weakly textured or motionless scenes, while standard cameras can still provide appearance information in this case. Thus, exploiting the complementarity of standard cameras and event cameras can effectively improve the performance of VPR algorithms. In the paper, we pro…
Rochester Institute of Technology（罗切斯特理工学院）；Adobe Research（Adobe 研究院）；Paige；Cornell Tech（康奈尔科技校区）
Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e.g. bar charts, pie charts, and line graphs. CQA requires capabilities that natural-image VQA algorithms lack: fine-grained measurements, optical character recognition, and handling out-of-vocabulary words in both questions and answers. Without modifications, state-of-the-art VQA algorithms perform poorly on this task. Here, we propose a novel CQA algorithm called parallel recurrent fusion of image and language (PReFIL). PReFIL first learn…
A robust and reliable semantic segmentation in adverse weather conditions is very important for autonomous cars, but most state-of-the-art approaches only achieve high accuracy rates in optimal weather conditions. The reason is that they are only optimized for good weather conditions and given noise models. However, most of them fail, if data with unknown disturbances occur, and their performance decrease enormously. One possibility to still obtain reliable results is to observe the environment with different sensor types, such as camera and lidar, and to fuse the sensor data by means of neura…
Weakly supervised multimodal segmentation of acoustic borehole images with depth-aware cross-attention
Federal University of Bahia, Institute of Geosciences, Department of Geophysics（巴伊亚联邦大学，地质科学学院，地球物理学系）；Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA)（地质物理中人工智能研究与应用小组）
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
Department of Psychology & Neuroscience, Auckland University of Technology（心理学与神经科学系，奥克兰技术大学）；Department of Psychiatry, University of Melbourne（精神病学系，墨尔本大学）
In this paper, we propose a novel deep convolutional neural network to solve the general multi-modal image restoration (MIR) and multi-modal image fusion (MIF) problems. Different from other methods based on deep learning, our network architecture is designed by drawing inspirations from a new proposed multi-modal convolutional sparse coding (MCSC) model. The key feature of the proposed network is that it can automatically split the common information shared among different modalities, from the unique information that belongs to each single modality, and is therefore denoted with CU-Net, i.e.,…
We address the multi-focus image fusion problem, where multiple images captured with different focal settings are to be fused into an all-in-focus image of higher quality. Algorithms for this problem necessarily admit the source image characteristics along with focused and blurred features. However, most sparsity-based approaches use a single dictionary in focused feature space to describe multi-focus images, and ignore the representations in blurred feature space. We propose a multi-focus image fusion approach based on sparse representation using a coupled dictionary. It exploits the observat…
Lightweight Interpretable RGB-Guided Hyperspectral Super-Resolution under Real Cross-resolution Misalignment
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS Grenoble INP（法国国家科学研究中心格勒诺布尔国立理工学院）；GIPSA-Lab（格勒诺布尔图像、信号、声学与自动化实验室）；Institut Universitaire de France (IUF)（法国大学研究院）
Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better classification. To address this shortcoming, in this paper, we propose three novel deep multilevel multimodal fusion frameworks to capitalize on different fusion strategies at various stages and to leverage the superiority of multilevel fusion. At input, we transform the depth data …
Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications. However, the limited resolution of light field images brings a lot of difficulties for further information display and extraction. In this paper, we introduce a novel learning-based framework to improve the spatial resolution of light fields. First, features from different dimensions are parallelly extracted and fused together in our multi-dimension fusion architecture. These features are then used to generate dynamic filters, which extract subpixel information from micro-lens imag…
University of Texas Southwestern Medical Center（德克萨斯大学西南医学中心）；School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；School of Traditional Chinese Medicine, Southern Medical University（南方医科大学中医学院）
To predict lung nodule malignancy with a high sensitivity and specificity, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine handcrafted features, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM) averaged from thirteen directions. We then trained 3D CNNs modified from three state-of-the-art 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract …
