Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from image-mesh misalignment, resulting in inaccurate reconstruction. In contrast, 3D keypoint estimation methods utilize the volumetric representation to achieve pixel-level accuracy but may predict unrealistic body structures. To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework. HybrIK directly transforms accurate 3D joints to body-part rotations via twist-and-swing decomposition. The swing rotations are analytically solved with 3D joints, while the twist rotations are derived from visual cues through neural networks. To capture comprehensive whole-body details, we further develop a holistic framework, HybrIK-X, which enhances HybrIK with articulated hands and an expressive face. HybrIK-X is fast and accurate by solving the whole-body pose with a one-stage model. Experiments demonstrate that HybrIK and HybrIK-X preserve both the accuracy of 3D joints and the realistic structure of the parametric human model, leading to pixel-aligned whole-body mesh recovery. The proposed method significantly surpasses the state-of-the-art methods on various benchmarks for body-only, hand-only, and whole-body scenarios. Code and results can be found at https://jeffli.site/HybrIK-X/
We propose a new 6-DoF grasp pose synthesis approach from 2D/2.5D input based on keypoints. Keypoint-based grasp detector from image input has demonstrated promising results in the previous study, where the additional visual information provided by color images compensates for the noisy depth perception. However, it relies heavily on accurately predicting the location of keypoints in the image space. In this paper, we devise a new grasp generation network that reduces the dependency on precise keypoint estimation. Given an RGB-D input, our network estimates both the grasp pose from keypoint detection as well as scale towards the camera. We further re-design the keypoint output space in order to mitigate the negative impact of keypoint prediction noise to Perspective-n-Point (PnP) algorithm. Experiments show that the proposed method outperforms the baseline by a large margin, validating the efficacy of our approach. Finally, despite trained on simple synthetic objects, our method demonstrate sim-to-real capacity by showing competitive results in real-world robot experiments.
One of the major challenges in multi-person pose estimation is instance-aware keypoint estimation. Previous methods address this problem by leveraging an off-the-shelf detector, heuristic post-grouping process or explicit instance identification process, hindering further improvements in the inference speed which is an important factor for practical applications. From the statistical point of view, those additional processes for identifying instances are necessary to bypass learning the high-dimensional joint distribution of human keypoints, which is a critical factor for another major challenge, the occlusion scenario. In this work, we propose a novel framework of single-stage instance-aware pose estimation by modeling the joint distribution of human keypoints with a mixture density model, termed as MDPose. Our MDPose estimates the distribution of human keypoints' coordinates using a mixture density model with an instance-aware keypoint head consisting simply of 8 convolutional layers. It is trained by minimizing the negative log-likelihood of the ground truth keypoints. Also, we propose a simple yet effective training strategy, Random Keypoint Grouping (RKG), which significantly alleviates the underflow problem leading to successful learning of relations between keypoints. On OCHuman dataset, which consists of images with highly occluded people, our MDPose achieves state-of-the-art performance by successfully learning the high-dimensional joint distribution of human keypoints. Furthermore, our MDPose shows significant improvement in inference speed with a competitive accuracy on MS COCO, a widely-used human keypoint dataset, thanks to the proposed much simpler single-stage pipeline.
We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB videos, and can decompose them into semantically meaningful parts that can be tracked and animated. Using a 3D autodecoder framework, paired with a keypoint estimator via a differentiable PnP algorithm, our model learns the underlying object geometry and parts decomposition in an entirely unsupervised manner. This allows it to perform 3D segmentation, 3D keypoint estimation, novel view synthesis, and animation. We primarily evaluate the framework on two video datasets: VoxCeleb $256^2$ and TEDXPeople $256^2$. In addition, on the Cats $256^2$ image dataset, we show it even learns compelling 3D geometry from still images. Finally, we show our model can obtain animatable 3D objects from a single or few images. Code and visual results available on our project website, see https://snap-research.github.io/unsupervised-volumetric-animation .
Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems. However, such annotations are not always available, especially for people performing unusual activities. In this paper, we propose an algorithm that learns to discover 3D keypoints on human bodies from multiple-view images without any supervision or labels other than the constraints multiple-view geometry provides. To ensure that the discovered 3D keypoints are meaningful, they are re-projected to each view to estimate the person's mask that the model itself has initially estimated without supervision. Our approach discovers more interpretable and accurate 3D keypoints compared to other state-of-the-art unsupervised approaches on Human3.6M and MPI-INF-3DHP benchmark datasets.
We propose a novel keypoint voting 6DoF object pose estimation method, which takes pure unordered point cloud geometry as input without RGB information. The proposed cascaded keypoint voting method, called RCVPose3D, is based upon a novel architecture which separates the task of semantic segmentation from that of keypoint regression, thereby increasing the effectiveness of both and improving the ultimate performance. The method also introduces a pairwise constraint in between different keypoints to the loss function when regressing the quantity for keypoint estimation, which is shown to be effective, as well as a novel Voter Confident Score which enhances both the learning and inference stages. Our proposed RCVPose3D achieves state-of-the-art performance on the Occlusion LINEMOD (74.5%) and YCB-Video (96.9%) datasets, outperforming existing pure RGB and RGB-D based methods, as well as being competitive with RGB plus point cloud methods.
Diagnosis based on medical images, such as X-ray images, often involves manual annotation of anatomical keypoints. However, this process involves significant human efforts and can thus be a bottleneck in the diagnostic process. To fully automate this procedure, deep-learning-based methods have been widely proposed and have achieved high performance in detecting keypoints in medical images. However, these methods still have clinical limitations: accuracy cannot be guaranteed for all cases, and it is necessary for doctors to double-check all predictions of models. In response, we propose a novel deep neural network that, given an X-ray image, automatically detects and refines the anatomical keypoints through a user-interactive system in which doctors can fix mispredicted keypoints with fewer clicks than needed during manual revision. Using our own collected data and the publicly available AASCE dataset, we demonstrate the effectiveness of the proposed method in reducing the annotation costs via extensive quantitative and qualitative results. A demo video of our approach is available on our project webpage.
Accurately annotated image datasets are essential components for studying animal behaviors from their poses. Compared to the number of species we know and may exist, the existing labeled pose datasets cover only a small portion of them, while building comprehensive large-scale datasets is prohibitively expensive. Here, we present a very data efficient strategy targeted for pose estimation in quadrupeds that requires only a small amount of real images from the target animal. It is confirmed that fine-tuning a backbone network with pretrained weights on generic image datasets such as ImageNet can mitigate the high demand for target animal pose data and shorten the training time by learning the the prior knowledge of object segmentation and keypoint estimation in advance. However, when faced with serious data scarcity (i.e., $<10^2$ real images), the model performance stays unsatisfactory, particularly for limbs with considerable flexibility and several comparable parts. We therefore introduce a prior-aware synthetic animal data generation pipeline called PASyn to augment the animal pose data essential for robust pose estimation. PASyn generates a probabilistically-valid synthetic pose dataset, SynAP, through training a variational generative model on several animated 3D animal models. In addition, a style transfer strategy is utilized to blend the synthetic animal image into the real backgrounds. We evaluate the improvement made by our approach with three popular backbone networks and test their pose estimation accuracy on publicly available animal pose images as well as collected from real animals in a zoo.
We present UnrealEgo, i.e., a new large-scale naturalistic dataset for egocentric 3D human pose estimation. UnrealEgo is based on an advanced concept of eyeglasses equipped with two fisheye cameras that can be used in unconstrained environments. We design their virtual prototype and attach them to 3D human models for stereo view capture. We next generate a large corpus of human motions. As a consequence, UnrealEgo is the first dataset to provide in-the-wild stereo images with the largest variety of motions among existing egocentric datasets. Furthermore, we propose a new benchmark method with a simple but effective idea of devising a 2D keypoint estimation module for stereo inputs to improve 3D human pose estimation. The extensive experiments show that our approach outperforms the previous state-of-the-art methods qualitatively and quantitatively. UnrealEgo and our source codes are available on our project web page.
We introduce a new synthetic data generator PSP-HDRI$+$ that proves to be a superior pre-training alternative to ImageNet and other large-scale synthetic data counterparts. We demonstrate that pre-training with our synthetic data will yield a more general model that performs better than alternatives even when tested on out-of-distribution (OOD) sets. Furthermore, using ablation studies guided by person keypoint estimation metrics with an off-the-shelf model architecture, we show how to manipulate our synthetic data generator to further improve model performance.
We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation, vision-and-language tasks such as region captioning and referring expression, to natural language processing tasks such as question answering and paraphrasing. Developing a single unified model for such a large variety of tasks poses unique challenges due to the heterogeneous inputs and outputs pertaining to each task, including RGB images, per-pixel maps, binary masks, bounding boxes, and language. We achieve this unification by homogenizing every supported input and output into a sequence of discrete vocabulary tokens. This common representation across all tasks allows us to train a single transformer-based architecture, jointly on over 90 diverse datasets in the vision and language fields. Unified-IO is the first model capable of performing all 7 tasks on the GRIT benchmark and produces strong results across 16 diverse benchmarks like NYUv2-Depth, ImageNet, VQA2.0, OK-VQA, Swig, VizWizGround, BoolQ, and SciTail, with no task-specific fine-tuning. Code and demos for Unified-IO are available at: https://unified-io.allenai.org.
Lane detection is a challenging task that requires predicting complex topology shapes of lane lines and distinguishing different types of lanes simultaneously. Earlier works follow a top-down roadmap to regress predefined anchors into various shapes of lane lines, which lacks enough flexibility to fit complex shapes of lanes due to the fixed anchor shapes. Lately, some works propose to formulate lane detection as a keypoint estimation problem to describe the shapes of lane lines more flexibly and gradually group adjacent keypoints belonging to the same lane line in a point-by-point manner, which is inefficient and time-consuming during postprocessing. In this paper, we propose a Global Association Network (GANet) to formulate the lane detection problem from a new perspective, where each keypoint is directly regressed to the starting point of the lane line instead of point-by-point extension. Concretely, the association of keypoints to their belonged lane line is conducted by predicting their offsets to the corresponding starting points of lanes globally without dependence on each other, which could be done in parallel to greatly improve efficiency. In addition, we further propose a Lane-aware Feature Aggregator (LFA), which adaptively captures the local correlations between adjacent keypoints to supplement local information to the global association. Extensive experiments on two popular lane detection benchmarks show that our method outperforms previous methods with F1 score of 79.63% on CULane and 97.71% on Tusimple dataset with high FPS. The code will be released at https://github.com/Wolfwjs/GANet.
People detection in top-view, fish-eye images is challenging as people in fish-eye images often appear in arbitrary directions and are distorted differently. Due to this unique radial geometry, axis-aligned people detectors often work poorly on fish-eye frames. Recent works account for this variability by modifying existing anchor-based detectors or relying on complex pre/post-processing. Anchor-based methods spread a set of pre-defined bounding boxes on the input image, most of which are invalid. In addition to being inefficient, this approach could lead to a significant imbalance between the positive and negative anchor boxes. In this work, we propose ARPD, a single-stage anchor-free fully convolutional network to detect arbitrarily rotated people in fish-eye images. Our network uses keypoint estimation to find the center point of each object and regress the object's other properties directly. To capture the various orientation of people in fish-eye cameras, in addition to the center and size, ARPD also predicts the angle of each bounding box. We also propose a periodic loss function that accounts for angle periodicity and relieves the difficulty of learning small-angle oscillations. Experimental results show that our method competes favorably with state-of-the-art algorithms while running significantly faster.
Learning intra-region contexts and inter-region relations are two effective strategies to strengthen feature representations for point cloud analysis. However, unifying the two strategies for point cloud representation is not fully emphasized in existing methods. To this end, we propose a novel framework named Point Relation-Aware Network (PRA-Net), which is composed of an Intra-region Structure Learning (ISL) module and an Inter-region Relation Learning (IRL) module. The ISL module can dynamically integrate the local structural information into the point features, while the IRL module captures inter-region relations adaptively and efficiently via a differentiable region partition scheme and a representative point-based strategy. Extensive experiments on several 3D benchmarks covering shape classification, keypoint estimation, and part segmentation have verified the effectiveness and the generalization ability of PRA-Net. Code will be available at https://github.com/XiwuChen/PRA-Net .
In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process. Motivated to find a more efficient solution, we propose to model individual keypoints and sets of spatially related keypoints (i.e., poses) as objects within a dense single-stage anchor-based detection framework. Hence, we call our method KAPAO (pronounced "Ka-Pow"), for Keypoints And Poses As Objects. KAPAO is applied to the problem of single-stage multi-person human pose estimation by simultaneously detecting human pose and keypoint objects and fusing the detections to exploit the strengths of both object representations. In experiments, we observe that KAPAO is faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. The accuracy-speed trade-off is especially favourable in the practical setting when not using test-time augmentation. Source code: https://github.com/wmcnally/kapao.
Automatic nuclei segmentation and classification play a vital role in digital pathology. However, previous works are mostly built on data with limited diversity and small sizes, making the results questionable or misleading in actual downstream tasks. In this paper, we aim to build a reliable and robust method capable of dealing with data from the 'the clinical wild'. Specifically, we study and design a new method to simultaneously detect, segment, and classify nuclei from Haematoxylin and Eosin (H&E) stained histopathology data, and evaluate our approach using the recent largest dataset: PanNuke. We address the detection and classification of each nuclei as a novel semantic keypoint estimation problem to determine the center point of each nuclei. Next, the corresponding class-agnostic masks for nuclei center points are obtained using dynamic instance segmentation. Meanwhile, we proposed a novel Joint Pyramid Fusion Module (JPFM) to model the cross-scale dependencies, thus enhancing the local feature for better nuclei detection and classification. By decoupling two simultaneous challenging tasks and taking advantage of JPFM, our method can benefit from class-aware detection and class-agnostic segmentation, thus leading to a significant performance boost. We demonstrate the superior performance of our proposed approach for nuclei segmentation and classification across 19 different tissue types, delivering new benchmark results.
A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation, i.e. a probability map that allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids, even allowing for sub-pixel coordinate accuracy. In this report, we aim to reproduce the findings of DARK that investigated the 2D heatmap representation by highlighting the importance of the encoding of the ground truth heatmap and the decoding of the predicted heatmap to keypoint coordinates. The authors claim that a) a more principled distribution-aware coordinate decoding method overcomes the limitations of the standard techniques widely used in the literature, and b), that the reconstruction of heatmaps from ground-truth coordinates by generating accurate and continuous heatmap distributions lead to unbiased model training, contrary to the standard coordinate encoding process that quantizes the keypoint coordinates on the resolution of the input image grid.
In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery reliably discover keypoints of aligned instances. However, when the target instances have high viewpoint or appearance variation, the discovered keypoints do not match the semantic correspondences over different images. Our work aims to discover keypoints even when the target instances have high viewpoint and appearance variation by using image-level supervision. Motivated by the weakly-supervised learning approach, our method exploits image-level supervision to identify discriminative parts and infer the viewpoint of the target instance. To discover diverse parts, we adopt a conditional image generation approach using a pair of images with structural deformation. Finally, we enforce a viewpoint-based equivariance constraint using the keypoints from the image-level supervision to resolve the spatial correlation problem that consistently appears in the images taken from various viewpoints. Our approach achieves state-of-the-art performance for the task of keypoint estimation on the limited supervision scenarios. Furthermore, the discovered keypoints are directly applicable to downstream tasks without requiring any keypoint labels.
In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surrounding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, which is not the case when using other grasp representations such as predefined grasp points. For instance, this property can be leveraged in motion optimization to define goal sets as implicit surface constraints in the robot configuration space. In this work, we restrict ourselves to the case of estimating possible end-effector positions directly from 2D camera images. To this extend, we define grasp manifolds via a set of key points and locate them in images using a Mask R-CNN backbone. Using learned features allows generalizing to different view angles, with potentially noisy images, and objects that were not part of the training set. We rely on simulation data only and perform experiments on simple and complex objects, including unseen ones. Our framework achieves an inference speed of 11.5 fps on a GPU, an average precision for keypoint estimation of 94.5% and a mean pixel distance of only 1.29. This shows that we can estimate the objects very well via bounding boxes and segmentation masks as well as approximate the correct grasp manifold's keypoint coordinates.
Rehabilitation is important to improve quality of life for mobility-impaired patients. Smart walkers are a commonly used solution that should embed automatic and objective tools for data-driven human-in-the-loop control and monitoring. However, present solutions focus on extracting few specific metrics from dedicated sensors with no unified full-body approach. We investigate a general, real-time, full-body pose estimation framework based on two RGB+D camera streams with non-overlapping views mounted on a smart walker equipment used in rehabilitation. Human keypoint estimation is performed using a two-stage neural network framework. The 2D-Stage implements a detection module that locates body keypoints in the 2D image frames. The 3D-Stage implements a regression module that lifts and relates the detected keypoints in both cameras to the 3D space relative to the walker. Model predictions are low-pass filtered to improve temporal consistency. A custom acquisition method was used to obtain a dataset, with 14 healthy subjects, used for training and evaluating the proposed framework offline, which was then deployed on the real walker equipment. An overall keypoint detection error of 3.73 pixels for the 2D-Stage and 44.05mm for the 3D-Stage were reported, with an inference time of 26.6ms when deployed on the constrained hardware of the walker. We present a novel approach to patient monitoring and data-driven human-in-the-loop control in the context of smart walkers. It is able to extract a complete and compact body representation in real-time and from inexpensive sensors, serving as a common base for downstream metrics extraction solutions, and Human-Robot interaction applications. Despite promising results, more data should be collected on users with impairments, to assess its performance as a rehabilitation tool in real-world scenarios.