Prior works employing pixel-based Gaussian representation have demonstrated efficacy in feed-forward sparseview reconstruction. However, such representation necessitates cross-view overlap for accurate depth estimation, and is challenged by object occlusions and frustum truncations. As a result, these methods require scene-centric data acquisition to maintain cross-view overlap and complete scene visibility to circumvent occlusions and truncations, which limits their applicability to scene-centric reconstruction. In contrast, in autonomous driving scenarios, a more practical paradigm is ego-centric reconstruction, which is characterized by minimal cross-view overlap and frequent occlusions and truncations. The limitations of pixel-based representation thus hinder the utility of prior works in this task. In light of this, this paper conducts an in-depth analysis of different representations, and introduces Omni-Gaussian representation with tailored network design to complement their strengths and mitigate their drawbacks. Experiments show that our method significantly surpasses state-of-the-art methods, pixelSplat and MVSplat, in ego-centric reconstruction, and achieves comparable performance to prior works in scene-centric reconstruction. Our code is available at https://github.com/WU-CVGL/Omni-Scene.

Simultaneous understanding and 3D reconstruction plays an important role in developing end-to-end embodied intelligent systems. To achieve this, recent approaches resort to 2D-to-3D feature alignment paradigm, which leads to limited 3D understanding capability and potential semantic information loss. In light of this, we propose SIU3R, the first alignment-free framework for generalizable simultaneous understanding and 3D reconstruction from unposed images. Specifically, SIU3R bridges reconstruction and understanding tasks via pixel-aligned 3D representation, and unifies multiple understanding tasks into a set of unified learnable queries, enabling native 3D understanding without the need of alignment with 2D models. To encourage collaboration between the two tasks with shared representation, we further conduct in-depth analyses of their mutual benefits, and propose two lightweight modules to facilitate their interaction. Extensive experiments demonstrate that our method achieves state-of-the-art performance not only on the individual tasks of 3D reconstruction and understanding, but also on the task of simultaneous understanding and 3D reconstruction, highlighting the advantages of our alignment-free framework and the effectiveness of the mutual benefit designs.

Weakly-supervised video anomaly detection (WS-VAD) aims to identify fine-grained anomalies from sparse video-level labels, which has gained increasing attention in recent years due to its various applications such as disaster warning and public security. Recent studies typically formulate WS-VAD as a multi-instance learning (MIL) problem. However, they neglect the instance creation process and simply apply a uniform temporal pooling (UTP) operation to obtain the training instances, leading to severe anomaly contamination and dilution. In this paper, we emphasize the importance of the instance modeling procedure and propose two simple yet effective modules, i.e., the dynamic segment merging (DSM) module and the retrieval-augmented anomaly restoration (RA2R) module, to tackle the problem from segment-level and feature-level, respectively. We equip various state-of-the-art WS-VAD models with the proposed methods and conduct thorough experiments on the challenging datasets, e.g., UCF-Crime, and XD-Violence. Results demonstrate the proposed method brings consistent performance improvement and establishes new state-of-the-art.

Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve the appearance details in synthesized images since the spatial correlation between the source and target is not fully exploited. To this end, we propose the Flow-based Dual Attention GAN (FDA-GAN) to apply occlusion- and deformation-aware feature fusion for higher generation quality. Specifically, deformable local attention and flow similarity attention, constituting the dual attention mechanism, can derive the output features responsible for deformable- and occlusion-aware fusion, respectively. Besides, to maintain the pose and global position consistency in transferring, we design a pose normalization network for learning adaptive normalization from the target pose to the source person. Both qualitative and quantitative results show that our method outperforms state-of-the-art models in public iPER and DeepFashion datasets.

The rapid development of flight control technology has made unmanned aerial vehicles (UAVs) widely used in high-precision strikes on the battlefield. The premise of this is to achieve accurate target recognition using UAV-based radars. Aiming at three typical ground targets, including pedestrians, wheeled vehicles, and tracked vehicles, the micro-Doppler modulation caused by the random vibration of the UAV is analyzed in this article for the first time. To improve the recognition accuracy under low signal-to-noise ratios (SNRs), Doppler signals are transformed into time–frequency images, and a deep convolutional denoising encoder (DCDE) is designed to effectively remove the noise without suppressing micro-Doppler characteristics. To avoid the complicated micro-Doppler feature extraction, deep residual learning that can reduce the burden of network training and gain higher learning efficiency compared with traditional deep convolutional neural networks (DCNNs) is adopted. Recognition results under various occasions using denoised micro-Doppler images and designed residual learning network indicate that the proposed method has higher precision and better robustness than current methods. Even when the SNR is only −16 dB, the overall recognition accuracy still exceeds 90%.

Human video motion transfer (HVMT) aims to synthesize videos that one person imitates other persons' actions. Although existing GAN-based HVMT methods have achieved great success, they either fail to preserve appearance details due to the loss of spatial consistency between synthesized and exemplary images, or generate incoherent video results due to the lack of temporal consistency among video frames. In this paper, we propose Coarse-to-Fine Flow Warping Network (C2F-FWN) for spatial-temporal consistent HVMT. Particularly, C2F-FWN utilizes coarse-to-fine flow warping and Layout-Constrained Deformable Convolution (LC-DConv) to improve spatial consistency, and employs Flow Temporal Consistency (FTC) Loss to enhance temporal consistency. In addition, provided with multi-source appearance inputs, C2F-FWN can support appearance attribute editing with great flexibility and efficiency. Besides public datasets, we also collected a large-scale HVMT dataset named SoloDance for evaluation. Extensive experiments conducted on our SoloDance dataset and the iPER dataset show that our approach outperforms state-of-art HVMT methods in terms of both spatial and temporal consistency. Source code and the SoloDance dataset are available at https://github.com/wswdx/C2F-FWN.

Human video motion transfer has a wide range of applications in multimedia, computer vision, and graphics. Recently, due to the rapid development of Generative Adversarial Networks (GANs), there has been significant progress in the field. However, almost all existing GAN-based works are prone to address the mapping from human motions to video scenes, with scene appearances encoded individually in the trained models. Therefore, each trained model can only generate videos with a specific scene appearance, and new models are required to be trained to generate new appearances. Besides, existing works lack the capability of appearance control. For example, users have to provide video records of wearing new clothes or performing in new backgrounds to enable clothes or background changing in their synthetic videos, which greatly limits the application flexibility. In this paper, we propose General Appearance-Controllable GAN (GAC-GAN), a general method for appearance-controllable human video motion transfer. To enable general-purpose appearance synthesis, we propose to include appearance information in the conditioning inputs. Thus, once trained, our model can generate new appearances by altering the input appearance information. To achieve appearance control, we first obtain the appearance-controllable conditioning inputs, and then utilize a two-stage GAC-GAN to generate the corresponding appearance-controllable outputs, where we utilize an Appearance-Consistency GAN (ACGAN) loss, and a shadow extraction module for output foreground, and background appearance control respectively. We further build a solo dance dataset containing a large number of dance videos for training, and evaluation. Experimental results on our solo dance dataset, and iPER dataset show that our proposed GAC-GAN can not only support appearance-controllable human video motion transfer but also achieve higher video quality than state-of-art methods.