We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
Thai Finger Spelling (TFS) sign recognition could benefit a community of hearing-difficulty people in bridging to a major hearing population. With a relatively large number of alphabets, TFS employs multiple signing schemes. Two schemes of more common signing -- static and dynamic single-hand signing, widely used in other sign languages -- have been addressed in several previous works. To complete the TFS sign recognition, the remaining two of quite distinct signing schemes -- static and dynamic point-on-hand signing -- need to be sufficiently addressed. With the advent of many off-the-shelf hand skeleton prediction models and that training a model to recognize a sign language from scratch is expensive, we explore an approach building upon recently launched MediaPipe Hands (MPH). MPH is a high-precision well-trained model for hand-keypoint detection. We have investigated MPH on three TFS schemes: static-single-hand (S1), simplified dynamic-single-hand (S2) and static-point-on-hand (P1) schemes. Our results show that MPH can satisfactorily address single-hand schemes with accuracy of 84.57% on both S1 and S2. However, our finding reveals a shortcoming of MPH in addressing a point-on-hand scheme, whose accuracy is 23.66% on P1 conferring to 69.19% obtained from conventional classification trained from scratch. This shortcoming has been investigated and attributed to self occlusion and handedness.
Ophthalmological imaging utilizes different imaging systems, such as color fundus, infrared, fluorescein angiography, optical coherence tomography (OCT) or OCT angiography. Multiple images with different modalities or acquisition times are often analyzed for the diagnosis of retinal diseases. Automatically aligning the vessel structures in the images by means of multi-modal registration can support the ophthalmologists in their work. Our method uses a convolutional neural network to extract features of the vessel structure in multi-modal retinal images. We jointly train a keypoint detection and description network on small patches using a classification and a cross-modal descriptor loss function and apply the network to the full image size in the test phase. Our method demonstrates the best registration performance on our and a public multi-modal dataset in comparison to competing methods.
Injury analysis may be one of the most beneficial applications of deep learning based human pose estimation. To facilitate further research on this topic, we provide an injury specific 2D dataset for alpine skiing, covering in total 533 images. We further propose a post processing routine, that combines rotational information with a simple kinematic model. We could improve detection results in fall situations by up to 21% regarding the [email omitted] metric.
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of learnable models based on deep networks. By leveraging traditional data augmentations and homography transformations, these networks learn to detect corners under adverse conditions such as extreme illumination changes. However, their generalization capabilities are limited to corner-like features detected a priori by classical methods or synthetically generated data. In this paper, we propose the Correspondence Network (CorrNet) that learns to detect repeatable keypoints and to extract discriminative descriptions via unsupervised contrastive learning under spatial constraints. Our experiments show that CorrNet is not only able to detect low-level features such as corners, but also high-level features that represent similar objects present in a pair of input images through our proposed joint guided backpropagation of their latent space. Our approach obtains competitive results under viewpoint changes and achieves state-of-the-art performance under illumination changes.
Keypoint detection plays an important role in a wide range of applications. However, predicting keypoints of small objects such as human hands is a challenging problem. Recent works fuse feature maps of deep Convolutional Neural Networks (CNNs), either via multi-level feature integration or multi-resolution aggregation. Despite achieving some success, the feature fusion approaches increase the complexity and the opacity of CNNs. To address this issue, we propose a novel CNN model named Multi-Scale Deep Supervision Network (P-MSDSNet) that learns feature maps at different scales with deep supervisions to produce attention maps for adaptive feature propagation from layers to layers. P-MSDSNet has a multi-stage architecture which makes it scalable while its deep supervision with spatial attention improves transparency to the feature learning at each stage. We show that P-MSDSNet outperforms the state-of-the-art approaches on benchmark datasets while requiring fewer number of parameters. We also show the application of P-MSDSNet to quantify finger tapping hand movements in a neuroscience study.
This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of volumetric medical image data. The primary operations of the 3D SIFT code are implemented on a graphics processing unit (GPU), including convolution, sub-sampling, and 4D peak detection from scale-space pyramids. The performance improvements are quantified in keypoint detection and image-to-image matching experiments, using 3D MRI human brain volumes of different people. Computationally efficient 3D keypoint descriptors are proposed based on the Binary Robust Independent Elementary Feature (BRIEF) code, including a novel descriptor we call Ranked Robust Independent Elementary Features (RRIEF), and compared to the original 3D SIFT-Rank method\citep{toews2013efficient}. The GPU implementation affords a speedup of approximately 7X beyond an optimised CPU implementation, where computation time is reduced from 1.4 seconds to 0.2 seconds for 3D volumes of size (145, 174, 145) voxels with approximately 3000 keypoints. Notable speedups include the convolution operation (20X), 4D peak detection (3X), sub-sampling (3X), and difference-of-Gaussian pyramid construction (2X). Efficient descriptors offer a speedup of 2X and a memory savings of 6X compared to standard SIFT-Rank descriptors, at a cost of reduced numbers of keypoint correspondences, revealing a trade-off between computational efficiency and algorithmic performance. The speedups gained by our implementation will allow for a more efficient analysis on larger data sets. Our optimized GPU implementation of the 3D SIFT-Rank extractor is available at https://github.com/CarluerJB/3D_SIFT_CUDA.
Current non-rigid object keypoint detectors perform well on a chosen kind of species and body parts, and require a large amount of labelled keypoints for training. Moreover, their heatmaps, tailored to specific body parts, cannot recognize novel keypoints (keypoints not labelled for training) on unseen species. We raise an interesting yet challenging question: how to detect both base (annotated for training) and novel keypoints for unseen species given a few annotated samples? Thus, we propose a versatile Few-shot Keypoint Detection (FSKD) pipeline, which can detect a varying number of keypoints of different kinds. Our FSKD provides the uncertainty estimation of predicted keypoints. Specifically, FSKD involves main and auxiliary keypoint representation learning, similarity learning, and keypoint localization with uncertainty modeling to tackle the localization noise. Moreover, we model the uncertainty across groups of keypoints by multivariate Gaussian distribution to exploit implicit correlations between neighboring keypoints. We show the effectiveness of our FSKD on (i) novel keypoint detection for unseen species, and (ii) few-shot Fine-Grained Visual Recognition (FGVR) and (iii) Semantic Alignment (SA) downstream tasks. For FGVR, detected keypoints improve the classification accuracy. For SA, we showcase a novel thin-plate-spline warping that uses estimated keypoint uncertainty under imperfect keypoint corespondences.
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint embeddings in a single forward pass, meaning the model is trained to track everything at once, or allocate their full capacity to a sparse predefined set of points, trading generality for accuracy. In this paper we explore a middle ground based on the observation that the number of relevant points at a given time are typically relatively few, e.g. grasp points on a target object. Our main contribution is a novel architecture, inspired by few-shot task adaptation, which allows a sparse-style network to condition on a keypoint embedding that indicates which point to track. Our central finding is that this approach provides the generality of dense-embedding models, while offering accuracy significantly closer to sparse-keypoint approaches. We present results illustrating this capacity vs. accuracy trade-off, and demonstrate the ability to zero-shot transfer to new object instances (within-class) using a real-robot pick-and-place task.
Existing methods detect the keypoints in a non-differentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a partially differentiable keypoint detection module, which outputs accurate sub-pixel keypoints. The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization. We also extract the descriptors in a sub-pixel way, and they are trained with the stable neural reprojection error loss. Moreover, a lightweight network is designed for keypoint detection and descriptor extraction, which can run at 95 frames per second for 640x480 images on a commercial GPU. On homography estimation, camera pose estimation, and visual (re-)localization tasks, the proposed method achieves equivalent performance with the state-of-the-art approaches, while greatly reduces the inference time.
This paper presents a new method to solve keypoint detection and instance association by using Transformer. For bottom-up multi-person pose estimation models, they need to detect keypoints and learn associative information between keypoints. We argue that these problems can be entirely solved by Transformer. Specifically, the self-attention in Transformer measures dependencies between any pair of locations, which can provide association information for keypoints grouping. However, the naive attention patterns are still not subjectively controlled, so there is no guarantee that the keypoints will always attend to the instances to which they belong. To address it we propose a novel approach of supervising self-attention for multi-person keypoint detection and instance association. By using instance masks to supervise self-attention to be instance-aware, we can assign the detected keypoints to their corresponding instances based on the pairwise attention scores, without using pre-defined offset vector fields or embedding like CNN-based bottom-up models. An additional benefit of our method is that the instance segmentation results of any number of people can be directly obtained from the supervised attention matrix, thereby simplifying the pixel assignment pipeline. The experiments on the COCO multi-person keypoint detection challenge and person instance segmentation task demonstrate the effectiveness and simplicity of the proposed method and show a promising way to control self-attention behavior for specific purposes.
We present neural radiance fields (NeRF) with templates, dubbed Template-NeRF, for modeling appearance and geometry and generating dense shape correspondences simultaneously among objects of the same category from only multi-view posed images, without the need of either 3D supervision or ground-truth correspondence knowledge. The learned dense correspondences can be readily used for various image-based tasks such as keypoint detection, part segmentation, and texture transfer that previously require specific model designs. Our method can also accommodate annotation transfer in a one or few-shot manner, given only one or a few instances of the category. Using periodic activation and feature-wise linear modulation (FiLM) conditioning, we introduce deep implicit templates on 3D data into the 3D-aware image synthesis pipeline NeRF. By representing object instances within the same category as shape and appearance variation of a shared NeRF template, our proposed method can achieve dense shape correspondences reasoning on images for a wide range of object classes. We demonstrate the results and applications on both synthetic and real-world data with competitive results compared with other methods based on 3D information.
Inferring 3D locations and shapes of multiple objects from a single 2D image is a long-standing objective of computer vision. Most of the existing works either predict one of these 3D properties or focus on solving both for a single object. One fundamental challenge lies in how to learn an effective representation of the image that is well-suited for 3D detection and reconstruction. In this work, we propose to learn a regular grid of 3D voxel features from the input image which is aligned with 3D scene space via a 3D feature lifting operator. Based on the 3D voxel features, our novel CenterNet-3D detection head formulates the 3D detection as keypoint detection in the 3D space. Moreover, we devise an efficient coarse-to-fine reconstruction module, including coarse-level voxelization and a novel local PCA-SDF shape representation, which enables fine detail reconstruction and one order of magnitude faster inference than prior methods. With complementary supervision from both 3D detection and reconstruction, one enables the 3D voxel features to be geometry and context preserving, benefiting both tasks.The effectiveness of our approach is demonstrated through 3D detection and reconstruction in single object and multiple object scenarios.
We study the problem of extracting correspondences between a pair of point clouds for registration. For correspondence retrieval, existing works benefit from matching sparse keypoints detected from dense points but usually struggle to guarantee their repeatability. To address this issue, we present CoFiNet - Coarse-to-Fine Network which extracts hierarchical correspondences from coarse to fine without keypoint detection. On a coarse scale and guided by a weighting scheme, our model firstly learns to match down-sampled nodes whose vicinity points share more overlap, which significantly shrinks the search space of a consecutive stage. On a finer scale, node proposals are consecutively expanded to patches that consist of groups of points together with associated descriptors. Point correspondences are then refined from the overlap areas of corresponding patches, by a density-adaptive matching module capable to deal with varying point density. Extensive evaluation of CoFiNet on both indoor and outdoor standard benchmarks shows our superiority over existing methods. Especially on 3DLoMatch where point clouds share less overlap, CoFiNet significantly outperforms state-of-the-art approaches by at least 5% on Registration Recall, with at most two-third of their parameters.
Bimodal palmprint recognition leverages palmprint and palm vein images simultaneously,which achieves high accuracy by multi-model information fusion and has strong anti-falsification property. In the recognition pipeline, the detection of palm and the alignment of region-of-interest (ROI) are two crucial steps for accurate matching. Most existing methods localize palm ROI by keypoint detection algorithms, however the intrinsic difficulties of keypoint detection tasks make the results unsatisfactory. Besides, the ROI alignment and fusion algorithms at image-level are not fully investigaged.To bridge the gap, in this paper, we propose Bimodal Palmprint Fusion Network (BPFNet) which focuses on ROI localization, alignment and bimodal image fusion.BPFNet is an end-to-end framework containing two subnets: The detection network directly regresses the palmprint ROIs based on bounding box prediction and conducts alignment by translation estimation.In the downstream,the bimodal fusion network implements bimodal ROI image fusion leveraging a novel proposed cross-modal selection scheme. To show the effectiveness of BPFNet,we carry out experiments on the large-scale touchless palmprint datasets CUHKSZ-v1 and TongJi and the proposed method achieves state-of-the-art performances.
We present a fast bottom-up method that jointly detects over 100 keypoints on humans or objects, also referred to as human/object pose estimation. We model all keypoints belonging to a human or an object -- the pose -- as a graph and leverage insights from community detection to quantify the independence of keypoints. We use a graph centrality measure to assign training weights to different parts of a pose. Our proposed measure quantifies how tightly a keypoint is connected to its neighborhood. Our experiments show that our method outperforms all previous methods for human pose estimation with fine-grained keypoint annotations on the face, the hands and the feet with a total of 133 keypoints. We also show that our method generalizes to car poses.
Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative paradigm that avoids the keypoint detection step. However, dense flow estimation is often inaccurate in the case of large displacements, occlusions, or homogeneous regions. In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches. We propose the Enhanced Probabilistic Dense Correspondence Network, PDC-Net+, capable of estimating accurate dense correspondences along with a reliable confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. In particular, we parametrize the predictive distribution as a constrained mixture model, ensuring better modelling of both accurate flow predictions and outliers. Moreover, we develop an architecture and an enhanced training strategy tailored for robust and generalizable uncertainty prediction in the context of self-supervised training. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets. We further validate the usefulness of our probabilistic confidence estimation for the tasks of pose estimation, 3D reconstruction, image-based localization, and image retrieval. Code and models are available at https://github.com/PruneTruong/DenseMatching.
This paper presents a new end-to-end semi-supervised framework to learn a dense keypoint detector using unlabeled multiview images. A key challenge lies in finding the exact correspondences between the dense keypoints in multiple views since the inverse of the keypoint mapping can be neither analytically derived nor differentiated. This limits applying existing multiview supervision approaches used to learn sparse keypoints that rely on the exact correspondences. To address this challenge, we derive a new probabilistic epipolar constraint that encodes the two desired properties. (1) Soft correspondence: we define a matchability, which measures a likelihood of a point matching to the other image's corresponding point, thus relaxing the requirement of the exact correspondences. (2) Geometric consistency: every point in the continuous correspondence fields must satisfy the multiview consistency collectively. We formulate a probabilistic epipolar constraint using a weighted average of epipolar errors through the matchability thereby generalizing the point-to-point geometric error to the field-to-field geometric error. This generalization facilitates learning a geometrically coherent dense keypoint detection model by utilizing a large number of unlabeled multiview images. Additionally, to prevent degenerative cases, we employ a distillation-based regularization by using a pretrained model. Finally, we design a new neural network architecture, made of twin networks, that effectively minimizes the probabilistic epipolar errors of all possible correspondences between two view images by building affinity matrices. Our method shows superior performance compared to existing methods, including non-differentiable bootstrapping in terms of keypoint accuracy, multiview consistency, and 3D reconstruction accuracy.
In this paper, we studied the problem of localizing a generic set of keypoints across multiple quadruped or four-legged animal species from images. Due to the lack of large scale animal keypoint dataset with ground truth annotations, we developed a novel dataset, AwA Pose, for keypoint detection of quadruped animals from images. Our dataset contains significantly more keypoints per animal and has much more diverse animals than the existing datasets for animal keypoint detection. We benchmarked the dataset with a state-of-the-art deep learning model for different keypoint detection tasks, including both seen and unseen animal cases. Experimental results showed the effectiveness of the dataset. We believe that this dataset will help the computer vision community in the design and evaluation of improved models for the generalized quadruped animal keypoint detection problem.
The goals of this research were to search for Convolutional Neural Network (CNN) architectures, suitable for an on-device processor with limited computing resources, performing at substantially lower Network Architecture Search (NAS) costs. A new algorithm entitled an Early Exit Population Initialisation (EE-PI) for Evolutionary Algorithm (EA) was developed to achieve both goals. The EE-PI reduces the total number of parameters in the search process by filtering the models with fewer parameters than the maximum threshold. It will look for a new model to replace those models with parameters more than the threshold. Thereby, reducing the number of parameters, memory usage for model storage and processing time while maintaining the same performance or accuracy. The search time was reduced to 0.52 GPU day. This is a huge and significant achievement compared to the NAS of 4 GPU days achieved using NSGA-Net, 3,150 GPU days by the AmoebaNet model, and the 2,000 GPU days by the NASNet model. As well, Early Exit Evolutionary Algorithm networks (EEEA-Nets) yield network architectures with minimal error and computational cost suitable for a given dataset as a class of network algorithms. Using EEEA-Net on CIFAR-10, CIFAR-100, and ImageNet datasets, our experiments showed that EEEA-Net achieved the lowest error rate among state-of-the-art NAS models, with 2.46% for CIFAR-10, 15.02% for CIFAR-100, and 23.8% for ImageNet dataset. Further, we implemented this image recognition architecture for other tasks, such as object detection, semantic segmentation, and keypoint detection tasks, and, in our experiments, EEEA-Net-C2 outperformed MobileNet-V3 on all of these various tasks. (The algorithm code is available at https://github.com/chakkritte/EEEA-Net).