In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our motivation is that regressing keypoint positions accurately needs to learn representations that focus on the keypoint regions. We present a simple yet effective approach, named disentangled keypoint regression (DEKR). We adopt adaptive convolutions through pixel-wise spatial transformer to activate the pixels in the keypoint regions and accordingly learn representations from them. We use a multi-branch structure for separate regression: each branch learns a representation with dedicated adaptive convolutions and regresses one keypoint. The resulting disentangled representations are able to attend to the keypoint regions, respectively, and thus the keypoint regression is spatially more accurate. We empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods and achieves superior bottom-up pose estimation results on two benchmark datasets, COCO and CrowdPose. The code and models are available at https://github.com/HRNet/DEKR.
We propose a new method for estimating the relative pose between two images, where we jointly learn keypoint detection, description extraction, matching and robust pose estimation. While our architecture follows the traditional pipeline for pose estimation from geometric computer vision, all steps are learnt in an end-to-end fashion, including feature matching. We demonstrate our method for the task of visual localization of a query image within a database of images with known pose. Pairwise pose estimation has many practical applications for robotic mapping, navigation, and AR. For example, the display of persistent AR objects in the scene relies on a precise camera localization to make the digital models appear anchored to the physical environment. We train our pipeline end-to-end specifically for the problem of visual localization. We evaluate our proposed approach on localization accuracy, robustness and runtime speed. Our method achieves state of the art localization accuracy on the 7 Scenes dataset.
The paper posits a computationally-efficient algorithm for multi-class facial image classification in which images are constrained with translation, rotation, scale, color, illumination and affine distortion. The proposed method is divided into five main building blocks including Haar-Cascade for face detection, Bilateral Filter for image preprocessing to remove unwanted noise, Affine Speeded-Up Robust Features (ASURF) for keypoint detection and description, Vector of Locally Aggregated Descriptors (VLAD) for feature quantization and Cloud Forest for image classification. The proposed method aims at improving the accuracy and the time taken for face recognition systems. The usage of the Cloud Forest algorithm as a classifier on three benchmark datasets, namely the FACES95, FACES96 and ORL facial datasets, showed promising results. The proposed methodology using Cloud Forest algorithm successfully improves the recognition model by 2-12\% when differentiated against other ensemble techniques like the Random Forest classifier depending upon the dataset used.
Generative adversarial networks (GANs) have attained photo-realistic quality in image generation. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN which is trained end-to-end on the classical GAN objective with internal conditioning on a set of space keypoints. These keypoints have associated appearance embeddings that respectively control the position and style of the generated objects and their parts. A major difficulty that we address with suitable network architectures and training schemes is disentangling the image into spatial and appearance factors without domain knowledge and supervision signals. We demonstrate that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging keypoint embeddings, such as generating portraits by combining the eyes, nose, and mouth from different images. In addition, the explicit generation of keypoints and matching images enables a new, GAN-based method for unsupervised keypoint detection.
With the advent of powerful, light-weight 3D LiDARs, they have become the hearth of many navigation and SLAM algorithms on various autonomous systems. Pointcloud registration methods working with unstructured pointclouds such as ICP are often computationally expensive or require a good initial guess. Furthermore, 3D feature-based registration methods have never quite reached the robustness of 2D methods in visual SLAM. With the continuously increasing resolution of LiDAR range images, these 2D methods not only become applicable but should exploit the illumination-independent modalities that come with it, such as depth and intensity. In visual SLAM, deep learned 2D features and descriptors perform exceptionally well compared to traditional methods. In this publication, we use a state-of-the-art 2D feature network as a basis for 3D3L, exploiting both intensity and depth of LiDAR range images to extract powerful 3D features. Our results show that these keypoints and descriptors extracted from LiDAR scan images outperform state-of-the-art on different benchmark metrics and allow for robust scan-to-scan alignment as well as global localization.
Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e. pre-training a model for image classification on the ILSVRC dataset, and then fine-tune on any target task. However, previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood. In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains (consumer photos, autonomous driving, aerial imagery, underwater, indoor scenes, synthetic, close-ups) and task types (semantic segmentation, object detection, depth estimation, keypoint detection). Importantly, these are all complex, structured output tasks types relevant to modern computer vision applications. In total we carry out over 2000 transfer learning experiments, including many where the source and target come from different image domains, task types, or both. We systematically analyze these experiments to understand the impact of image domain, task type, and dataset size on transfer learning performance. Our study leads to several insights and concrete recommendations: (1) for most tasks there exists a source which significantly outperforms ILSVRC'12 pre-training; (2) the image domain is the most important factor for achieving positive transfer; (3) the source dataset should \emph{include} the image domain of the target dataset to achieve best results; (4) at the same time, we observe only small negative effects when the image domain of the source task is much broader than that of the target; (5) transfer across task types can be beneficial, but its success is heavily dependent on both the source and target task types.
We propose a new end-to-end trainable approach for multi-instance pose estimation by combining a convolutional neural network with a transformer. We cast multi-instance pose estimation from images as a direct set prediction problem. Inspired by recent work on end-to-end trainable object detection with transformers, we use a transformer encoder-decoder architecture together with a bipartite matching scheme to directly regress the pose of all individuals in a given image. Our model, called POse Estimation Transformer (POET), is trained using a novel set-based global loss that consists of a keypoint loss, a keypoint visibility loss, a center loss and a class loss. POET reasons about the relations between detected humans and the full image context to directly predict the poses in parallel. We show that POET can achieve high accuracy on the challenging COCO keypoint detection task. To the best of our knowledge, this model is the first end-to-end trainable multi-instance human pose estimation method.
Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to video sequences. Prevalent shortcomings include the failure to handle motion blur, video defocus, or pose occlusions, arising from the inability in capturing the temporal dependency among video frames. On the other hand, directly employing conventional recurrent neural networks incurs empirical difficulties in modeling spatial contexts, especially for dealing with pose occlusions. In this paper, we propose a novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection. Three modular components are designed in our framework. A Pose Temporal Merger encodes keypoint spatiotemporal context to generate effective searching scopes while a Pose Residual Fusion module computes weighted pose residuals in dual directions. These are then processed via our Pose Correction Network for efficient refining of pose estimations. Our method ranks No.1 in the Multi-frame Person Pose Estimation Challenge on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018. We have released our code, hoping to inspire future research.
Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. Though many DA theories and algorithms have been proposed, most of them are tailored into classification settings and may fail in regression tasks, especially in the practical keypoint detection task. To tackle this difficult but significant task, we present a method of regressive domain adaptation (RegDA) for unsupervised keypoint detection. Inspired by the latest theoretical work, we first utilize an adversarial regressor to maximize the disparity on the target domain and train a feature generator to minimize this disparity. However, due to the high dimension of the output space, this regressor fails to detect samples that deviate from the support of the source. To overcome this problem, we propose two important ideas. First, based on our observation that the probability density of the output space is sparse, we introduce a spatial probability distribution to describe this sparsity and then use it to guide the learning of the adversarial regressor. Second, to alleviate the optimization difficulty in the high-dimensional space, we innovatively convert the minimax game in the adversarial training to the minimization of two opposite goals. Extensive experiments show that our method brings large improvement by 8% to 11% in terms of PCK on different datasets.
Many image-based perception tasks can be formulated as detecting, associating and tracking semantic keypoints, e.g., human body pose estimation and tracking. In this work, we present a general framework that jointly detects and forms spatio-temporal keypoint associations in a single stage, making this the first real-time pose detection and tracking algorithm. We present a generic neural network architecture that uses Composite Fields to detect and construct a spatio-temporal pose which is a single, connected graph whose nodes are the semantic keypoints (e.g., a person's body joints) in multiple frames. For the temporal associations, we introduce the Temporal Composite Association Field (TCAF) which requires an extended network architecture and training method beyond previous Composite Fields. Our experiments show competitive accuracy while being an order of magnitude faster on multiple publicly available datasets such as COCO, CrowdPose and the PoseTrack 2017 and 2018 datasets. We also show that our method generalizes to any class of semantic keypoints such as car and animal parts to provide a holistic perception framework that is well suited for urban mobility such as self-driving cars and delivery robots.
Keypoint detection and description is a commonly used building block in computer vision systems particularly for robotics and autonomous driving. However, the majority of techniques to date have focused on standard cameras with little consideration given to fisheye cameras which are commonly used in urban driving and automated parking. In this paper, we propose a novel training and evaluation pipeline for fisheye images. We make use of SuperPoint as our baseline which is a self-supervised keypoint detector and descriptor that has achieved state-of-the-art results on homography estimation. We introduce a fisheye adaptation pipeline to enable training on undistorted fisheye images. We evaluate the performance on the HPatches benchmark, and, by introducing a fisheye based evaluation method for detection repeatability and descriptor matching correctness, on the Oxford RobotCar dataset.
A key assumption of top-down human pose estimation approaches is their expectation of having a single person/instance present in the input bounding box. This often leads to failures in crowded scenes with occlusions. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Instance Pose Network (MIPNet) allows for predicting multiple 2D pose instances within a given bounding box. We introduce a Multi-Instance Modulation Block (MIMB) that can adaptively modulate channel-wise feature responses for each instance and is parameter efficient. We demonstrate the efficacy of our approach by evaluating on COCO, CrowdPose, and OCHuman datasets. Specifically, we achieve 70.0 AP on CrowdPose and 42.5 AP on OCHuman test sets, a significant improvement of 2.4 AP and 6.5 AP over the prior art, respectively. When using ground truth bounding boxes for inference, MIPNet achieves an improvement of 0.7 AP on COCO, 0.9 AP on CrowdPose, and 9.1 AP on OCHuman validation sets compared to HRNet. Interestingly, when fewer, high confidence bounding boxes are used, HRNet's performance degrades (by 5 AP) on OCHuman, whereas MIPNet maintains a relatively stable performance (drop of 1 AP) for the same inputs.
Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that exhibit large variations in poses that greatly influence their visual appearance, such as wild animals. However, supervised training of a keypoint detection network requires annotating a large image dataset for each animal species, which is a labor-intensive task. To reduce the need for labeled data, we propose to learn simultaneously keypoint heatmaps and pose invariant keypoint representations in a semi-supervised manner using a small set of labeled images along with a larger set of unlabeled images. Keypoint representations are learnt with a semantic keypoint consistency constraint that forces the keypoint detection network to learn similar features for the same keypoint across the dataset. Pose invariance is achieved by making keypoint representations for the image and its augmented copies closer together in feature space. Our semi-supervised approach significantly outperforms previous methods on several benchmarks for human and animal body landmark localization.
Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathematically, but rather through natural task specification. In this paper, we present Learning by Watching (LbW), an algorithmic framework for policy learning through imitation from a single video specifying the task. The key insights of our method are two-fold. First, since the human arms may not have the same morphology as robot arms, our framework learns unsupervised human to robot translation to overcome the morphology mismatch issue. Second, to capture the details in salient regions that are crucial for learning state representations, our model performs unsupervised keypoint detection on the translated robot videos. The detected keypoints form a structured representation that contains semantically meaningful information and can be used directly for computing reward and policy learning. We evaluate the effectiveness of our LbW framework on five robot manipulation tasks, including reaching, pushing, sliding, coffee making, and drawer closing. Extensive experimental evaluations demonstrate that our method performs favorably against the state-of-the-art approaches.
While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces Transformer for human pose estimation. The attention layers built in Transformer enable our model to capture long-range relationships efficiently and also can reveal what dependencies the predicted keypoints rely on. To predict keypoint heatmaps, the last attention layer acts as an aggregator, which collects contributions from image clues and forms maximum positions of keypoints. Such a heatmap-based localization approach via Transformer conforms to the principle of Activation Maximization~\cite{erhan2009visualizing}. And the revealed dependencies are image-specific and fine-grained, which also can provide evidence of how the model handles special cases, e.g., occlusion. The experiments show that TransPose achieves 75.8 AP and 75.0 AP on COCO validation and test-dev sets, while being more lightweight and faster than mainstream CNN architectures. The TransPose model also transfers very well on MPII benchmark, achieving superior performance on the test set when fine-tuned with small training costs. Code and pre-trained models are publicly available\footnote{\url{https://github.com/yangsenius/TransPose}}.
Keypoints of objects reflect their concise abstractions, while the corresponding connection links (CL) build the skeleton by detecting the intrinsic relations between keypoints. Existing approaches are typically computationally-intensive, inapplicable for instances belonging to multiple classes, and/or infeasible to simultaneously encode connection information. To address the aforementioned issues, we propose an end-to-end category-implicit Keypoint and Link Prediction Network (KLPNet), which is the first approach for simultaneous semantic keypoint detection (for multi-class instances) and CL rejuvenation. In our KLPNet, a novel Conditional Link Prediction Graph is proposed for link prediction among keypoints that are contingent on a predefined category. Furthermore, a Cross-stage Keypoint Localization Module (CKLM) is introduced to explore feature aggregation for coarse-to-fine keypoint localization. Comprehensive experiments conducted on three publicly available benchmarks demonstrate that our KLPNet consistently outperforms all other state-of-the-art approaches. Furthermore, the experimental results of CL prediction also show the effectiveness of our KLPNet with respect to occlusion problems.
Keypoint detection is an essential component for the object registration and alignment. In this work, we reckon keypoint detection as information compression, and force the model to distill out irrelevant points of an object. Based on this, we propose UKPGAN, a general self-supervised 3D keypoint detector where keypoints are detected so that they could reconstruct the original object shape. Two modules: GAN-based keypoint sparsity control and salient information distillation modules are proposed to locate those important keypoints. Extensive experiments show that our keypoints align well with human annotated keypoint labels, and can be applied to SMPL human bodies under various non-rigid deformations. Furthermore, our keypoint detector trained on clean object collections generalizes well to real-world scenarios, thus further improves geometric registration when combined with off-the-shelf point descriptors. Repeatability experiments show that our model is stable under both rigid and non-rigid transformations, with local reference frame estimation. Our code is available on https://github.com/qq456cvb/UKPGAN.
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores. Panoptic Quality (PQ), a measure proposed for evaluating panoptic segmentation (Kirillov et al., 2019), does not suffer from these limitations but is limited to panoptic segmentation. In this paper, we propose Localisation Recall Precision (LRP) Error as the average matching error of a visual detector computed based on both its localisation and classification qualities for a given confidence score threshold. LRP Error, initially proposed only for object detection by Oksuz et al. (2018), does not suffer from the aforementioned limitations and is applicable to all visual detection tasks. We also introduce Optimal LRP (oLRP) Error as the minimum LRP Error obtained over confidence scores to evaluate visual detectors and obtain optimal thresholds for deployment. We provide a detailed comparative analysis of LRP Error with AP and PQ, and use nearly 100 state-of-the-art visual detectors from seven visual detection tasks (i.e. object detection, keypoint detection, instance segmentation, panoptic segmentation, visual relationship detection, zero-shot detection and generalised zero-shot detection) using ten datasets to empirically show that LRP Error provides richer and more discriminative information than its counterparts. Code available at: https://github.com/kemaloksuz/LRP-Error
Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks. Hypothesizing that neural architecture search holds great potential for human pose estimation, we explore the application of neuroevolution, a form of neural architecture search inspired by biological evolution, in the design of 2D human pose networks for the first time. Additionally, we propose a new weight transfer scheme that enables us to accelerate neuroevolution in a flexible manner. Our method produces network designs that are more efficient and more accurate than state-of-the-art hand-designed networks. In fact, the generated networks process images at higher resolutions using less computation than previous hand-designed networks at lower resolutions, allowing us to push the boundaries of 2D human pose estimation. Our base network designed via neuroevolution, which we refer to as EvoPose2D-S, achieves comparable accuracy to SimpleBaseline while being 50% faster and 12.7x smaller in terms of file size. Our largest network, EvoPose2D-L, achieves new state-of-the-art accuracy on the Microsoft COCO Keypoints benchmark, is 4.3x smaller than its nearest competitor, and has similar inference speed. The code is publicly available at https://github.com/wmcnally/evopose2d.
The success of deep neural networks in the traditional keypoint detection task encourages researchers to solve new problems and collect more complex datasets. The size of the DeepFashion2 dataset poses a new challenge on the keypoint detection task, as it comprises 13 clothing categories that span a wide range of keypoints (294 in total). The direct prediction of all keypoints leads to huge memory consumption, slow training, and a slow inference time. This paper studies the keypoint grouping approach and how it affects the performance of the CenterNet architecture. We propose a simple and efficient automatic grouping technique with a powerful post-processing method and apply it to the DeepFashion2 fashion landmark task and the MS COCO pose estimation task. This reduces memory consumption and processing time during inference by up to 19% and 30% respectively, and during the training stage by 28% and 26% respectively, without compromising accuracy.