Multi-view camera-based 3D object detection has gained popularity due to its low cost. But accurately inferring 3D geometry solely from camera data remains challenging, which impacts model performance. One promising approach to address this issue is to distill precise 3D geometry knowledge from LiDAR data. However, transferring knowledge between different sensor modalities is hindered by the significant modality gap. In this paper, we approach this challenge from the perspective of both architecture design and knowledge distillation and present a new simulated multi-modal 3D object detection method named BEVSimDet. We first introduce a novel framework that includes a LiDAR and camera fusion-based teacher and a simulated multi-modal student, where the student simulates multi-modal features with image-only input. To facilitate effective distillation, we propose a simulated multi-modal distillation scheme that supports intra-modal, cross-modal, and multi-modal distillation simultaneously, in Bird's-eye-view (BEV) space. By combining them together, BEVSimDet can learn better feature representations for 3D object detection while enjoying cost-effective camera-only deployment. Experimental results on the challenging nuScenes benchmark demonstrate the effectiveness and superiority of BEVSimDet over recent representative methods. The source code will be released at \href{https://github.com/ViTAE-Transformer/BEVSimDet}{BEVSimDet}.
Neural radiance field (NeRF) has become a popular 3D representation method for human avatar reconstruction due to its high-quality rendering capabilities, e.g., regarding novel views and poses. However, previous methods for editing the geometry and appearance of the avatar only allow for global editing through body shape parameters and 2D texture maps. In this paper, we propose a new approach named \textbf{U}nified \textbf{V}olumetric \textbf{A}vatar (\textbf{UVA}) that enables local and independent editing of both geometry and texture, while retaining the ability to render novel views and poses. UVA transforms each observation point to a canonical space using a skinning motion field and represents geometry and texture in separate neural fields. Each field is composed of a set of structured latent codes that are attached to anchor nodes on a deformable mesh in canonical space and diffused into the entire space via interpolation, allowing for local editing. To address spatial ambiguity in code interpolation, we use a local signed height indicator. We also replace the view-dependent radiance color with a pose-dependent shading factor to better represent surface illumination in different poses. Experiments on multiple human avatars demonstrate that our UVA achieves competitive results in novel view synthesis and novel pose rendering while enabling local and independent editing of geometry and appearance. The source code will be released.
Image matting refers to extracting precise alpha matte from natural images, and it plays a critical role in various downstream applications, such as image editing. Despite being an ill-posed problem, traditional methods have been trying to solve it for decades. The emergence of deep learning has revolutionized the field of image matting and given birth to multiple new techniques, including automatic, interactive, and referring image matting. This paper presents a comprehensive review of recent advancements in image matting in the era of deep learning. We focus on two fundamental sub-tasks: auxiliary input-based image matting, which involves user-defined input to predict the alpha matte, and automatic image matting, which generates results without any manual intervention. We systematically review the existing methods for these two tasks according to their task settings and network structures and provide a summary of their advantages and disadvantages. Furthermore, we introduce the commonly used image matting datasets and evaluate the performance of representative matting methods both quantitatively and qualitatively. Finally, we discuss relevant applications of image matting and highlight existing challenges and potential opportunities for future research. We also maintain a public repository to track the rapid development of deep image matting at https://github.com/JizhiziLi/matting-survey.
Estimating Click-Through Rate (CTR) is a vital yet challenging task in personalized product search. However, existing CTR methods still struggle in the product search settings due to the following three challenges including how to more effectively extract users' short-term interests with respect to multiple aspects, how to extract and fuse users' long-term interest with short-term interests, how to address the entangling characteristic of long and short-term interests. To resolve these challenges, in this paper, we propose a new approach named Hierarchical Interests Fusing Network (HIFN), which consists of four basic modules namely Short-term Interests Extractor (SIE), Long-term Interests Extractor (LIE), Interests Fusion Module (IFM) and Interests Disentanglement Module (IDM). Specifically, SIE is proposed to extract user's short-term interests by integrating three fundamental interests encoders within it namely query-dependent, target-dependent and causal-dependent interest encoder, respectively, followed by delivering the resultant representation to the module LIE, where it can effectively capture user long-term interests by devising an attention mechanism with respect to the short-term interests from SIE module. In IFM, the achieved long and short-term interests are further fused in an adaptive manner, followed by concatenating it with original raw context features for the final prediction result. Last but not least, considering the entangling characteristic of long and short-term interests, IDM further devises a self-supervised framework to disentangle long and short-term interests. Extensive offline and online evaluations on a real-world e-commerce platform demonstrate the superiority of HIFN over state-of-the-art methods.
Siamese trackers based on 3D region proposal network (RPN) have shown remarkable success with deep Hough voting. However, using a single seed point feature as the cue for voting fails to produce high-quality 3D proposals. Additionally, the equal treatment of seed points in the voting process, regardless of their significance, exacerbates this limitation. To address these challenges, we propose a novel transformer-based voting scheme to generate better proposals. Specifically, a global-local transformer (GLT) module is devised to integrate object- and patch-aware geometric priors into seed point features, resulting in robust and accurate cues for offset learning of seed points. To train the GLT module, we introduce an importance prediction branch that learns the potential importance weights of seed points as a training constraint. Incorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds. Moreover, we identify that the highest-scored proposal in the Siamese paradigm may not be the most accurate proposal, which limits tracking performance. Towards this concern, we approach the binary score prediction task as a ranking problem, and design a target-aware ranking loss and a localization-aware ranking loss to produce accurate ranking of proposals. With the ranking losses, we further present GLT-T++, an enhanced version of GLT-T. Extensive experiments on multiple benchmarks demonstrate that our GLT-T and GLT-T++ outperform state-of-the-art methods in terms of tracking accuracy while maintaining a real-time inference speed. The source code will be made available at https://github.com/haooozi/GLT-T.
Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibility of transformers to adapt to objects of varying sizes, shapes, and orientations. To address this issue, we propose a novel quadrangle attention (QA) method that extends the window-based attention to a general quadrangle formulation. Our method employs an end-to-end learnable quadrangle regression module that predicts a transformation matrix to transform default windows into target quadrangles for token sampling and attention calculation, enabling the network to model various targets with different shapes and orientations and capture rich context information. We integrate QA into plain and hierarchical vision transformers to create a new architecture named QFormer, which offers minor code modifications and negligible extra computational cost. Extensive experiments on public benchmarks demonstrate that QFormer outperforms existing representative vision transformers on various vision tasks, including classification, object detection, semantic segmentation, and pose estimation. The code will be made publicly available at \href{https://github.com/ViTAE-Transformer/QFormer}{QFormer}.
The creation of 2D realistic facial images and 3D face shapes using generative networks has been a hot topic in recent years. Existing face generators exhibit exceptional performance on faces in small to medium poses (with respect to frontal faces) but struggle to produce realistic results for large poses. The distorted rendering results on large poses in 3D-aware generators further show that the generated 3D face shapes are far from the distribution of 3D faces in reality. We find that the above issues are caused by the training dataset's pose imbalance. In this paper, we present LPFF, a large-pose Flickr face dataset comprised of 19,590 high-quality real large-pose portrait images. We utilize our dataset to train a 2D face generator that can process large-pose face images, as well as a 3D-aware generator that can generate realistic human face geometry. To better validate our pose-conditional 3D-aware generators, we develop a new FID measure to evaluate the 3D-level performance. Through this novel FID measure and other experiments, we show that LPFF can help 2D face generators extend their latent space and better manipulate the large-pose data, and help 3D-aware face generators achieve better view consistency and more realistic 3D reconstruction results.
Federated learning, which allows multiple client devices in a network to jointly train a machine learning model without direct exposure of clients' data, is an emerging distributed learning technique due to its nature of privacy preservation. However, it has been found that models trained with federated learning usually have worse performance than their counterparts trained in the standard centralized learning mode, especially when the training data is imbalanced. In the context of federated learning, data imbalance may occur either locally one one client device, or globally across many devices. The complexity of different types of data imbalance has posed challenges to the development of federated learning technique, especially considering the need of relieving data imbalance issue and preserving data privacy at the same time. Therefore, in the literature, many attempts have been made to handle class imbalance in federated learning. In this paper, we present a detailed review of recent advancements along this line. We first introduce various types of class imbalance in federated learning, after which we review existing methods for estimating the extent of class imbalance without the need of knowing the actual data to preserve data privacy. After that, we discuss existing methods for handling class imbalance in FL, where the advantages and disadvantages of the these approaches are discussed. We also summarize common evaluation metrics for class imbalanced tasks, and point out potential future directions.
Camera calibration involves estimating camera parameters to infer geometric features from captured sequences, which is crucial for computer vision and robotics. However, conventional calibration is laborious and requires dedicated collection. Recent efforts show that learning-based solutions have the potential to be used in place of the repeatability works of manual calibrations. Among these solutions, various learning strategies, networks, geometric priors, and datasets have been investigated. In this paper, we provide a comprehensive survey of learning-based camera calibration techniques, by analyzing their strengths and limitations. Our main calibration categories include the standard pinhole camera model, distortion camera model, cross-view model, and cross-sensor model, following the research trend and extended applications. As there is no benchmark in this community, we collect a holistic calibration dataset that can serve as a public platform to evaluate the generalization of existing methods. It comprises both synthetic and real-world data, with images and videos captured by different cameras in diverse scenes. Toward the end of this paper, we discuss the challenges and provide further research directions. To our knowledge, this is the first survey for the learning-based camera calibration (spanned 8 years). The summarized methods, datasets, and benchmarks are available and will be regularly updated at https://github.com/KangLiao929/Awesome-Deep-Camera-Calibration.