Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection.To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters. In particular, we introduce a human-joint GCN, which unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.
Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of the training data. Moreover, many of these methods are not designed or trained under severe occlusion explicitly, making their performance on handling occlusion compromised. Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation. As humans in videos may appear in different scales and have various motion speeds, we apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multi-stride temporal convolutional networks (TCNs) to estimate 3D joints or keypoints. Furthermore, we design a spatio-temporal discriminator based on body structures as well as limb motions to assess whether the predicted pose forms a valid pose and a valid movement. During training, we explicitly mask out some keypoints to simulate various occlusion cases, from minor to severe occlusion, so that our network can learn better and becomes robust to various degrees of occlusion. As there are limited 3D ground-truth data, we further utilize 2D video data to inject a semi-supervised learning capability to our network. Moreover, we observe that there is a discrepancy between 3D pose prediction and 2D pose estimation due to different pose variations between video and image training datasets. We, therefore propose a confidence-based inference stage optimization to adaptively enforce 3D pose projection to match 2D pose estimation to further improve final pose prediction accuracy. Experiments on public datasets validate the effectiveness of our method, and our ablation studies show the strengths of our network's individual submodules.
Occlusion is a long-standing problem that causes many modern tracking methods to be erroneous. In this paper, we address the occlusion problem by exploiting the current and future possible locations of the target object from its past trajectory. To achieve this, we introduce a learning-based tracking method that takes into account background motion modeling and trajectory prediction. Our trajectory prediction module predicts the target object's locations in the current and future frames based on the object's past trajectory. Since, in the input video, the target object's trajectory is not only affected by the object motion but also the camera motion, our background motion module estimates the camera motion. So that the object's trajectory can be made independent from it. To dynamically switch between the appearance-based tracker and the trajectory prediction, we employ a network that can assess how good a tracking prediction is, and we use the assessment scores to choose between the appearance-based tracker's prediction and the trajectory-based prediction. Comprehensive evaluations show that the proposed method sets a new state-of-the-art performance on commonly used tracking benchmarks.
A few methods have been proposed to estimate the CRF from a single image, however most of them tend to fail in handling general real images. For instance, EdgeCRF based on patches extracted from colour edges works effectively only when the presence of noise is insignificant, which is not the case for many real images; and, CRFNet, a recent method based on fully supervised deep learning works only for the CRFs that are in the training data, and hence fail to deal with other possible CRFs beyond the training data. To address these problems, we introduce a non-deep-learning method using prediction consistency and gradual refinement. First, we rely more on the patches of the input image that provide more consistent predictions. If the predictions from a patch are more consistent, it means that the patch is likely to be less affected by noise or any inferior colour combinations, and hence, it can be more reliable for CRF estimation. Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model's complexity to improve the estimation. This is because a simple model, while being less accurate, overfits less to noise than a complex model does. Our experiments confirm that our method outperforms the existing single-image methods for both daytime and nighttime real images.
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or the motion is too fast/slow relative to the scale and speed of the training data. Moreover, to our knowledge, many of these methods are not designed or trained under severe occlusion explicitly, making their performance on handling occlusion compromised. Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation. As humans in videos may appear in different scales and have various motion speeds, we apply multi-scale spatial features for 2D joints or keypoints prediction in each individual frame, and multi-stride temporal convolutional net-works (TCNs) to estimate 3D joints or keypoints. Furthermore, we design a spatio-temporal discriminator based on body structures as well as limb motions to assess whether the predicted pose forms a valid pose and a valid movement. During training, we explicitly mask out some keypoints to simulate various occlusion cases, from minor to severe occlusion, so that our network can learn better and becomes robust to various degrees of occlusion. As there are limited 3D ground-truth data, we further utilize 2D video data to inject a semi-supervised learning capability to our network. Experiments on public datasets validate the effectiveness of our method, and our ablation studies show the strengths of our network\'s individual submodules.
In dense foggy scenes, existing optical flow methods are erroneous. This is due to the degradation caused by dense fog particles that break the optical flow basic assumptions such as brightness and gradient constancy. To address the problem, we introduce a semi-supervised deep learning technique that employs real fog images without optical flow ground-truths in the training process. Our network integrates the domain transformation and optical flow networks in one framework. Initially, given a pair of synthetic fog images, its corresponding clean images and optical flow ground-truths, in one training batch we train our network in a supervised manner. Subsequently, given a pair of real fog images and a pair of clean images that are not corresponding to each other (unpaired), in the next training batch, we train our network in an unsupervised manner. We then alternate the training of synthetic and real data iteratively. We use real data without ground-truths, since to have ground-truths in such conditions is intractable, and also to avoid the overfitting problem of synthetic data training, where the knowledge learned on synthetic data cannot be generalized to real data testing. Together with the network architecture design, we propose a new training strategy that combines supervised synthetic-data training and unsupervised real-data training. Experimental results show that our method is effective and outperforms the state-of-the-art methods in estimating optical flow in dense foggy scenes.
The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future directions.
Most existing methods of depth from stereo are designed for daytime scenes, where the lighting can be assumed to be sufficiently bright and more or less uniform. Unfortunately, this assumption does not hold for nighttime scenes, causing the existing methods to be erroneous when deployed in nighttime. Nighttime is not only about low light, but also about glow, glare, non-uniform distribution of light, etc. One of the possible solutions is to train a network on nighttime images in a fully supervised manner. However, to obtain proper disparity ground-truths that are dense, independent from glare/glow, and can have sufficiently far depth ranges is extremely intractable. In this paper, to address the problem of depth from stereo in nighttime, we introduce a joint translation and stereo network that is robust to nighttime conditions. Our method uses no direct supervision and does not require ground-truth disparities of the nighttime training images. First, we utilize a translation network that can render realistic nighttime stereo images from given daytime stereo images. Second, we train a stereo network on the rendered nighttime images using the available disparity supervision from the daytime images, and simultaneously also train the translation network to gradually improve the rendered nighttime images. We introduce a stereo-consistency constraint into our translation network to ensure that the translated pairs are stereo-consistent. Our experiments show that our joint translation-stereo network outperforms the state-of-the-art methods.
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark. The documentation first starts with the background and motivation of the dataset. Follow it, we briefly describe the method of collecting the dataset and the processing method from raw dataset to the final release dataset, specifically, the version 1.0. We also provide the detailed usage of the dataset and the evaluation metric for submitted the result for the 2019 Hyperspectral City Challenge.