Composed pose retrieval (CPR) enables users to search for human poses by specifying a reference pose and a transition description, but progress in this field is hindered by the scarcity and inconsistency of annotated pose transitions. Existing CPR datasets rely on costly human annotations or heuristic-based rule generation, both of which limit scalability and diversity. In this work, we introduce AutoComPose, the first framework that leverages multimodal large language models (MLLMs) to automatically generate rich and structured pose transition descriptions. Our method enhances annotation quality by structuring transitions into fine-grained body part movements and introducing mirrored/swapped variations, while a cyclic consistency constraint ensures logical coherence between forward and reverse transitions. To advance CPR research, we construct and release two dedicated benchmarks, AIST-CPR and PoseFixCPR, supplementing prior datasets with enhanced attributes. Extensive experiments demonstrate that training retrieval models with AutoComPose yields superior performance over human-annotated and heuristic-based methods, significantly reducing annotation costs while improving retrieval quality. Our work pioneers the automatic annotation of pose transitions, establishing a scalable foundation for future CPR research.
Reconstructing from multi-view images is a longstanding problem in 3D vision, where neural radiance fields (NeRFs) have shown great potential and get realistic rendered images of novel views. Currently, most NeRF methods either require accurate camera poses or a large number of input images, or even both. Reconstructing NeRF from few-view images without poses is challenging and highly ill-posed. To address this problem, we propose CAD-NeRF, a method reconstructed from less than 10 images without any known poses. Specifically, we build a mini library of several CAD models from ShapeNet and render them from many random views. Given sparse-view input images, we run a model and pose retrieval from the library, to get a model with similar shapes, serving as the density supervision and pose initializations. Here we propose a multi-view pose retrieval method to avoid pose conflicts among views, which is a new and unseen problem in uncalibrated NeRF methods. Then, the geometry of the object is trained by the CAD guidance. The deformation of the density field and camera poses are optimized jointly. Then texture and density are trained and fine-tuned as well. All training phases are in self-supervised manners. Comprehensive evaluations of synthetic and real images show that CAD-NeRF successfully learns accurate densities with a large deformation from retrieved CAD models, showing the generalization abilities.
Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types. In response, we introduce Sitcom-Crafter, a comprehensive and extendable system for human motion generation in 3D space, which can be guided by extensive plot contexts to enhance workflow efficiency for anime and game designers. The system is comprised of eight modules, three of which are dedicated to motion generation, while the remaining five are augmentation modules that ensure consistent fusion of motion sequences and system functionality. Central to the generation modules is our novel 3D scene-aware human-human interaction module, which addresses collision issues by synthesizing implicit 3D Signed Distance Function (SDF) points around motion spaces, thereby minimizing human-scene collisions without additional data collection costs. Complementing this, our locomotion and human-scene interaction modules leverage existing methods to enrich the system's motion generation capabilities. Augmentation modules encompass plot comprehension for command generation, motion synchronization for seamless integration of different motion types, hand pose retrieval to enhance motion realism, motion collision revision to prevent human collisions, and 3D retargeting to ensure visual fidelity. Experimental evaluations validate the system's ability to generate high-quality, diverse, and physically realistic motions, underscoring its potential for advancing creative workflows.
This paper introduces an open-source interface for American Sign Language fingerspell recognition and semantic pose retrieval, aimed to serve as a stepping stone towards more advanced sign language translation systems. Utilizing a combination of convolutional neural networks and pose estimation models, the interface provides two modular components: a recognition module for translating ASL fingerspelling into spoken English and a production module for converting spoken English into ASL pose sequences. The system is designed to be highly accessible, user-friendly, and capable of functioning in real-time under varying environmental conditions like backgrounds, lighting, skin tones, and hand sizes. We discuss the technical details of the model architecture, application in the wild, as well as potential future enhancements for real-world consumer applications.
Image-to-point cloud registration seeks to estimate their relative camera pose, which remains an open question due to the data modality gaps. The recent matching-based methods tend to tackle this by building 2D-3D correspondences. In this paper, we reveal the information loss inherent in these methods and propose a matching-free paradigm, named MaFreeI2P. Our key insight is to actively retrieve the camera pose in SE(3) space by contrasting the geometric features between the point cloud and the query image. To achieve this, we first sample a set of candidate camera poses and construct their cost volume using the cross-modal features. Superior to matching, cost volume can preserve more information and its feature similarity implicitly reflects the confidence level of the sampled poses. Afterwards, we employ a convolutional network to adaptively formulate a similarity assessment function, where the input cost volume is further improved by filtering and pose-based weighting. Finally, we update the camera pose based on the similarity scores, and adopt a heuristic strategy to iteratively shrink the pose sampling space for convergence. Our MaFreeI2P achieves a very competitive registration accuracy and recall on the KITTI-Odometry and Apollo-DaoxiangLake datasets.
We present an automated and efficient approach for retrieving high-quality CAD models of objects and their poses in a scene captured by a moving RGB-D camera. We first investigate various objective functions to measure similarity between a candidate CAD object model and the available data, and the best objective function appears to be a "render-and-compare" method comparing depth and mask rendering. We thus introduce a fast-search method that approximates an exhaustive search based on this objective function for simultaneously retrieving the object category, a CAD model, and the pose of an object given an approximate 3D bounding box. This method involves a search tree that organizes the CAD models and object properties including object category and pose for fast retrieval and an algorithm inspired by Monte Carlo Tree Search, that efficiently searches this tree. We show that this method retrieves CAD models that fit the real objects very well, with a speed-up factor of 10x to 120x compared to exhaustive search.
We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans. Through a visual evaluation by 3D experts, we show that our method retrieves annotations that are at least as accurate as manual annotations, and can thus be used as ground truth without the burden of manually annotating 3D data. We do this using an analysis-by-synthesis approach, which compares renderings of the CAD models with the captured scene. We introduce a 'cloning procedure' that identifies objects that have the same geometry, to annotate these objects with the same CAD models. This allows us to obtain complete annotations for the ScanNet dataset and the recent ARKitScenes dataset.
Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivial task due to appearance variations between similar poses and similarities between dissimilar poses. Instead, we follow the key idea that comparing two poses is easier than directly predicting one. Render-and-compare approaches have been employed to that end, however, they tend to be unstable, computationally expensive, and slow for real-time applications. We propose doing category-level pose estimation by learning an alignment metric in an embedding space using a contrastive loss with a dynamic margin and a continuous pose-label space. For efficient inference, we use a simple real-time image retrieval scheme with a pre-rendered and pre-embedded reference set of renderings. To achieve robustness to real-world conditions, we employ synthetic occlusions, bounding box perturbations, and appearance augmentations. Our approach achieves state-of-the-art performance on PASCAL3D and OccludedPASCAL3D and surpasses the competing methods on KITTI3D in a cross-dataset evaluation setting. The code is currently available at https://github.com/gkouros/contrastive-pose-retrieval.
The recent success of transformer models in language, such as BERT, has motivated the use of such architectures for multi-modal feature learning and tasks. However, most multi-modal variants (e.g., ViLBERT) have limited themselves to visual-linguistic data. Relatively few have explored its use in audio-visual modalities, and none, to our knowledge, illustrate them in the context of granular audio-visual detection or segmentation tasks such as sound source separation and localization. In this work, we introduce TriBERT -- a transformer-based architecture, inspired by ViLBERT, which enables contextual feature learning across three modalities: vision, pose, and audio, with the use of flexible co-attention. The use of pose keypoints is inspired by recent works that illustrate that such representations can significantly boost performance in many audio-visual scenarios where often one or more persons are responsible for the sound explicitly (e.g., talking) or implicitly (e.g., sound produced as a function of human manipulating an object). From a technical perspective, as part of the TriBERT architecture, we introduce a learned visual tokenization scheme based on spatial attention and leverage weak-supervision to allow granular cross-modal interactions for visual and pose modalities. Further, we supplement learning with sound-source separation loss formulated across all three streams. We pre-train our model on the large MUSIC21 dataset and demonstrate improved performance in audio-visual sound source separation on that dataset as well as other datasets through fine-tuning. In addition, we show that the learned TriBERT representations are generic and significantly improve performance on other audio-visual tasks such as cross-modal audio-visual-pose retrieval by as much as 66.7% in top-1 accuracy.
Human pose information is a critical component in many downstream image processing tasks, such as activity recognition and motion tracking. Likewise, a pose estimator for the illustrated character domain would provide a valuable prior for assistive content creation tasks, such as reference pose retrieval and automatic character animation. But while modern data-driven techniques have substantially improved pose estimation performance on natural images, little work has been done for illustrations. In our work, we bridge this domain gap by efficiently transfer-learning from both domain-specific and task-specific source models. Additionally, we upgrade and expand an existing illustrated pose estimation dataset, and introduce two new datasets for classification and segmentation subtasks. We then apply the resultant state-of-the-art character pose estimator to solve the novel task of pose-guided illustration retrieval. All data, models, and code will be made publicly available.
Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend. However, such exercises are hard to follow without expert guidance (which is impossible to scale for personalized feedback to every trainee remotely). Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. We collect descriptions of correcting a "current" pose to look like a "target" pose (in both English and Hindi). The collected descriptions have interesting linguistic properties such as egocentric relations to environment objects, analogous references, etc., requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e.g., homes, offices). From our dataset, we introduce the pose-correctional-captioning task and its reverse target-pose-retrieval task. During the correctional-captioning task, models must generate descriptions of how to move from the current to target pose image, whereas in the retrieval task, models should select the correct target pose given the initial pose and correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (object-match, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. To verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images.
Object pose estimation is an integral part of robot vision and AR. Previous 6D pose retrieval pipelines treat the problem either as a regression task or discretize the pose space to classify. We change this paradigm and reformulate the problem as an action decision process where an initial pose is updated in incremental discrete steps that sequentially move a virtual 3D rendering towards the correct solution. A neural network estimates likely moves from a single RGB image iteratively and determines so an acceptable final pose. In comparison to other approaches that train object-specific pose models, we learn a decision process. This allows for a lightweight architecture while it naturally generalizes to unseen objects. A coherent stop action for process termination enables dynamic reduction of the computation cost if there are insignificant changes in a video sequence. Instead of a static inference time, we thereby automatically increase the runtime depending on the object motion. Robustness and accuracy of our action decision network are evaluated on Laval and YCB video scenes where we significantly improve the state-of-the-art.
Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multiple views. This ability is useful for analyzing body movements and human behaviors in images and videos. In this paper, we propose an approach for learning a compact view-invariant embedding space from 2D joint keypoints alone, without explicitly predicting 3D poses. Since 2D poses are projected from 3D space, they have an inherent ambiguity, which is difficult to represent through a deterministic mapping. Hence, we use probabilistic embeddings to model this input uncertainty. Experimental results show that our embedding model achieves higher accuracy when retrieving similar poses across different camera views, in comparison with 2D-to-3D pose lifting models. We also demonstrate the effectiveness of applying our embeddings to view-invariant action recognition and video alignment. Our code is available at https://github.com/google-research/google-research/tree/master/poem.
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal relations in multi-view videos to arrive at a multi-view consistent pose embedding. When jointly trained with limited 3D pose annotations, our approach improves the baseline by 25% and state-of-the-art by 8.7%, whilst using substantially smaller networks. Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.
The growing popularity of autonomous systems creates a need for reliable and efficient metric pose retrieval algorithms. Currently used approaches tend to rely on nearest neighbor search of binary descriptors to perform the 2D-3D matching and guarantee realtime capabilities on mobile platforms. These methods struggle, however, with the growing size of the map, changes in viewpoint or appearance, and visual aliasing present in the environment. The rigidly defined descriptor patterns only capture a limited neighborhood of the keypoint and completely ignore the overall visual context. We propose LandmarkBoost - an approach that, in contrast to the conventional 2D-3D matching methods, casts the search problem as a landmark classification task. We use a boosted classifier to classify landmark observations and directly obtain correspondences as classifier scores. We also introduce a formulation of visual context that is flexible, efficient to compute, and can capture relationships in the entire image plane. The original binary descriptors are augmented with contextual information and informative features are selected by the boosting framework. Through detailed experiments, we evaluate the retrieval quality and performance of LandmarkBoost, demonstrating that it outperforms common state-of-the-art descriptor matching methods.
One major challenge for 3D pose estimation from a single RGB image is the acquisition of sufficient training data. In particular, collecting large amounts of training data that contain unconstrained images and are annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of images with annotated 2D poses and the second source consists of accurate 3D motion capture data. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient and robust 3D pose retrieval. In our experiments, we show that our approach achieves state-of-the-art results and is even competitive when the skeleton structure of the two sources differ substantially.
In this paper, for the first time, we introduce a multiple instance (MI) deep hashing technique for learning discriminative hash codes with weak bag-level supervision suited for large-scale retrieval. We learn such hash codes by aggregating deeply learnt hierarchical representations across bag members through a dedicated MI pool layer. For better trainability and retrieval quality, we propose a two-pronged approach that includes robust optimization and training with an auxiliary single instance hashing arm which is down-regulated gradually. We pose retrieval for tumor assessment as an MI problem because tumors often coexist with benign masses and could exhibit complementary signatures when scanned from different anatomical views. Experimental validations on benchmark mammography and histology datasets demonstrate improved retrieval performance over the state-of-the-art methods.
In this work we address the challenging problem of 3D human pose estimation from single images. Recent approaches learn deep neural networks to regress 3D pose directly from images. One major challenge for such methods, however, is the collection of training data. Specifically, collecting large amounts of training data containing unconstrained images annotated with accurate 3D poses is infeasible. We therefore propose to use two independent training sources. The first source consists of accurate 3D motion capture data, and the second source consists of unconstrained images with annotated 2D poses. To integrate both sources, we propose a dual-source approach that combines 2D pose estimation with efficient 3D pose retrieval. To this end, we first convert the motion capture data into a normalized 2D pose space, and separately learn a 2D pose estimation model from the image data. During inference, we estimate the 2D pose and efficiently retrieve the nearest 3D poses. We then jointly estimate a mapping from the 3D pose space to the image and reconstruct the 3D pose. We provide a comprehensive evaluation of the proposed method and experimentally demonstrate the effectiveness of our approach, even when the skeleton structures of the two sources differ substantially.
In this work, we propose a method for object recognition and pose estimation from depth images using convolutional neural networks. Previous methods addressing this problem rely on manifold learning to learn low dimensional viewpoint descriptors and employ them in a nearest neighbor search on an estimated descriptor space. In comparison we create an efficient multi-task learning framework combining manifold descriptor learning and pose regression. By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching. By in depth experimental evaluation of the novel loss function we observed that the view descriptors learned by the network are much more discriminative resulting in almost 30% increase regarding relative pose accuracy compared to related works. On the other hand, regarding directly regressed poses we obtained important improvement compared to simple pose regression. By leveraging the advantages of both manifold learning and regression tasks, we are able to improve the current state-of-the-art for object recognition and pose retrieval that we demonstrate through in depth experimental evaluation.