Local processing is an essential feature of CNNs and other neural network architectures - it is one of the reasons why they work so well on images where relevant information is, to a large extent, local. However, perspective effects stemming from the projection in a conventional camera vary for different global positions in the image. We introduce Perspective Crop Layers (PCLs) - a form of perspective crop of the region of interest based on the camera geometry - and show that accounting for the perspective consistently improves the accuracy of state-of-the-art 3D pose reconstruction methods. PCLs are modular neural network layers, which, when inserted into existing CNN and MLP architectures, deterministically remove the location-dependent perspective effects while leaving end-to-end training and the number of parameters of the underlying neural network unchanged. We demonstrate that PCL leads to improved 3D human pose reconstruction accuracy for CNN architectures that use cropping operations, such as spatial transformer networks (STN), and, somewhat surprisingly, MLPs used for 2D-to-3D keypoint lifting. Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike. PCL offers an easy way to improve the accuracy of existing 3D reconstruction networks by making them geometry aware. Our code is publicly available at github.com/yu-frank/PerspectiveCropLayers.
SenseTime Research（商汤科技研究院）；JD.com, Inc（京东集团）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））
Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images. We discover that the principal reasons of Uni6D performance limitations are Instance-Outside and Instance-Inside noise. Uni6D's simple pipeline design inherently introduces Instance-Outside noise from background pixels in the receptive field, while ignoring Instance-Inside noise in the input depth data. In this paper, we propose a two-step denoising approach for dealing with the aforementioned noise in Uni6D. To reduce noise from non-instance regions, an insta…
UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys
University of Minnesota, Twin Cities（明尼苏达大学双城校区）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；University of Pittsburgh（匹兹堡大学）；Max Planck Institute for Biogeochemistry（马克斯·普朗克生物地球化学研究所）；Boston University（波士顿大学）；Peking University（北京大学）
SenseTime Research（商汤科技研究院）；University of Chinese Academy of Sciences（中国科学院大学）
As RGB-D sensors become more affordable, using RGB-D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones to extract features for RGB and depth images. They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion. We find that the essential reason for using two independent backbones is the "projection breakdown" problem. In the depth image plane, the projected 3D structure of the physical world is preserved by the 1D depth value and …
This paper studies the task of any objects grasping from the known categories by free-form language instructions. This task demands the technique in computer vision, natural language processing, and robotics. We bring these disciplines together on this open challenge, which is essential to human-robot interaction. Critically, the key challenge lies in inferring the category of objects from linguistic instructions and accurately estimating the 6-DoF information of unseen objects from the known classes. In contrast, previous works focus on inferring the pose of object candidates at the instance …
Dyson Robotics Lab, Imperial College London（戴森机器人实验室，帝国理工学院）
Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks. This is partly due to the fact that reinforcement learning algorithms are notoriously difficult and time consuming to train, which is exacerbated when training from images rather than full-state inputs. As humans perform manipulation tasks, our eyes closely monitor every step of the process with our gaze focusing sequentially on the objects being manipulated. With this in mind, we present our Attention-driven Robotic Manipulation (A…
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
College of Computer Science, Nankai University（南开大学计算机科学学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；Horizon Robotics（地平线机器人）；D-Robotics
Object pose estimation is a crucial prerequisite for robots to perform autonomous manipulation in clutter. Real-world bin-picking settings such as warehouses present additional challenges, e.g., new objects are added constantly. Most of the existing object pose estimation methods assume that 3D models of the objects is available beforehand. We present a pipeline that requires minimal human intervention and circumvents the reliance on the availability of 3D models by a fast data acquisition method and a synthetic data generation procedure. This work builds on previous work on semantic segmentat…
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）
We present a new approach for a single view, image-based object pose estimation. Specifically, the problem of culling false positives among several pose proposal estimates is addressed in this paper. Our proposed approach targets the problem of inaccurate confidence values predicted by CNNs which is used by many current methods to choose a final object pose prediction. We present a network called CullNet, solving this task. CullNet takes pairs of pose masks rendered from a 3D model and cropped regions in the original image as input. This is then used to calibrate the confidence scores of the p…
A comprehensive review of 3D convolutional neural network-based classification techniques of diseased and defective crops using non-UAV-based hyperspectral images
Institute of Computer Science, FORTH（FORTH 计算机科学研究所）；Computer Science Department, UOC（克里特大学计算机科学系）
We present a method for the real-time estimation of the full 3D pose of one or more human hands using a single commodity RGB camera. Recent work in the area has displayed impressive progress using RGBD input. However, since the introduction of RGBD sensors, there has been little progress for the case of monocular color input. We capitalize on the latest advancements of deep learning, combining them with the power of generative hand pose estimation techniques to achieve real-time monocular 3D hand pose estimation in unrestricted scenarios. More specifically, given an RGB image and the relevant …
Agriculture is vital for human survival and remains a major driver of several economies around the world; more so in underdeveloped and developing economies. With increasing demand for food and cash crops, due to a growing global population and the challenges posed by climate change, there is a pressing need to increase farm outputs while incurring minimal costs. Previous machine vision technologies developed for selective weeding have faced the challenge of reliable and accurate weed detection. We present approaches for plant seedlings classification with a dataset that contains 4,275 images …
RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学北京信息科学与技术国家研究中心）；School of Computer Science and Informatics, Cardiff University（卡迪夫大学计算机科学与信息学院）
EPFL（洛桑联邦理工学院）；Balgrist University Hospital（巴尔格里斯特大学医院）；University of Zurich（苏黎世大学）；The University of British Columbia（英属哥伦比亚大学）
In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn sensors, which are cumbersome to setup, or manual image annotation, which is time consuming. We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras. By contrast to classical markerless motion capture solutions, we allow cameras to rotate freely so that large capture volumes can be covered. In a first step, tight crops around the skier are predicted and fed to a …
Differently from 2D image datasets such as COCO, large-scale human datasets with 3D ground-truth annotations are very difficult to obtain in the wild. In this paper, we address this problem by augmenting existing 2D datasets with high-quality 3D pose fits. Remarkably, the resulting annotations are sufficient to train from scratch 3D pose regressor networks that outperform the current state-of-the-art on in-the-wild benchmarks such as 3DPW. Additionally, training on our augmented data is straightforward as it does not require to mix multiple and incompatible 2D and 3D datasets or to use complic…
This work presents a novel Convolutional Neural Network (CNN) architecture and a training procedure to enable robust and accurate pose estimation of a noncooperative spacecraft. First, a new CNN architecture is introduced that has scored a fourth place in the recent Pose Estimation Challenge hosted by Stanford's Space Rendezvous Laboratory (SLAB) and the Advanced Concepts Team (ACT) of the European Space Agency (ESA). The proposed architecture first detects the object by regressing a 2D bounding box, then a separate network regresses the 2D locations of the known surface keypoints from an imag…
Seoul National University（首尔国立大学）；Soong-sil University（崇实大学）
Individual tooth segmentation from cone beam computed tomography (CBCT) images is an essential prerequisite for an anatomical understanding of orthodontic structures in several applications, such as tooth reformation planning and implant guide simulations. However, the presence of severe metal artifacts in CBCT images hinders the accurate segmentation of each individual tooth. In this study, we propose a neural network for pixel-wise labeling to exploit an instance segmentation framework that is robust to metal artifacts. Our method comprises of three steps: 1) image cropping and realignment b…
Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high resolution image or crop it into small patches for separate processing. In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy. We propose collaborative Global-Local Networks (GLNet) to effectively preserve both global and local information in a highly memory-efficient manner. GLNet is composed of a gl…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland University（萨尔大学）；Universidad Rey Juan Carlos（胡安卡洛斯国王大学）
We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleto…
NVIDIA（英伟达）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Emotion recognition aims to interpret the emotional states of a person based on various inputs including audio, visual, and textual cues. This paper focuses on emotion recognition using visual features. To leverage the correlation between facial expression and the emotional state of a person, pioneering methods rely primarily on facial features. However, facial features are often unreliable in natural unconstrained scenarios, such as in crowded scenes, as the face lacks pixel resolution and contains artifacts due to occlusion and blur. To address this, in the wild emotion recognition exploits …
South China University of Technology（华南理工大学）；UBTech Sydney Artificial Intelligence Institute（优必选悉尼人工智能研究院）；The University of Sydney（悉尼大学）
Human faces in surveillance videos often suffer from severe image blur, dramatic pose variations, and occlusion. In this paper, we propose a comprehensive framework based on Convolutional Neural Networks (CNN) to overcome challenges in video-based face recognition (VFR). First, to learn blur-robust face representations, we artificially blur training data composed of clear still images to account for a shortfall in real-world video training data. Using training data composed of both still images and artificially blurred data, CNN is encouraged to learn blur-insensitive features automatically. S…
SWNet: A Cross-Spectral Network for Camouflaged Weed Detection
ESPOL Polytechnic University（ESPOL多科技术大学）；Research Center for Information and Communication Technologies (CITIC-UGR)（信息与通信技术研究中心（CITIC-UGR））；University of Granada（格拉纳达大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
This work focuses on complete 3D facial geometry prediction, including 3D facial alignment via 3D face modeling and face orientation estimation using the proposed multi-task, multi-modal, and multi-representation landmark refinement network (M$^3$-LRN). Our focus is on the important facial attributes, 3D landmarks, and we fully utilize their embedded information to guide 3D facial geometry learning. We first propose a multi-modal and multi-representation feature aggregation for landmark refinement. Next, we are the first to study 3DMM regression from sparse 3D landmarks and utilize multi-repre…
National Tsing Hua University（国立清华大学）；Virginia Tech（弗吉尼亚理工学院暨州立大学）
Image colorization is inherently an ill-posed problem with multi-modal uncertainty. Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly. Although these learning-based methods have shown impressive performance, they usually fail on the input images that contain multiple objects. The leading cause is that existing models perform learning and colorization on the entire image. In the absence of a clear figure-ground separation, these models cannot effectively locate and learn meaningful object-level semantics. In this paper, we propos…
University of Colorado at Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
Deep neural networks are facing a potential security threat from adversarial examples, inputs that look normal but cause an incorrect classification by the deep neural network. For example, the proposed threat could result in hand-written digits on a scanned check being incorrectly classified but looking normal when humans see them. This research assesses the extent to which adversarial examples pose a security threat, when one considers the normal image acquisition process. This process is mimicked by simulating the transformations that normally occur in acquiring the image in a real world ap…
