Xiuping Liu

Hongchen Tan, Xiuping Liu, Baocai Yin et al.

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent distribution, which can help the discriminator better distinguish synthesized images from real images. DNM also adopts a Distribution Adversarial Loss (DAL) to guide the generator to align with normalized real image distributions in the latent space. Extensive experiments on two public datasets demonstrated that our DR-GAN achieved a competitive performance in the Text-to-Image task.

Juntao Jian, Xiuping Liu, Manyi Li et al.

How human interact with objects depends on the functional roles of the target objects, which introduces the problem of affordance-aware hand-object interaction. It requires a large number of human demonstrations for the learning and understanding of plausible and appropriate hand-object interactions. In this work, we present AffordPose, a large-scale dataset of hand-object interactions with affordance-driven hand pose. We first annotate the specific part-level affordance labels for each object, e.g. twist, pull, handle-grasp, etc, instead of the general intents such as use or handover, to indicate the purpose and guide the localization of the hand-object interactions. The fine-grained hand-object interactions reveal the influence of hand-centered affordances on the detailed arrangement of the hand poses, yet also exhibit a certain degree of diversity. We collect a total of 26.7K hand-object interactions, each including the 3D object shape, the part-level affordance label, and the manually adjusted hand poses. The comprehensive data analysis shows the common characteristics and diversity of hand-object interactions per affordance via the parameter statistics and contacting computation. We also conduct experiments on the tasks of hand-object affordance understanding and affordance-oriented hand-object interaction generation, to validate the effectiveness of our dataset in learning the fine-grained hand-object interactions. Project page: https://github.com/GentlesJan/AffordPose.

Hongchen Tan, Baocai Yin, Kun Wei et al.

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.

Wei Song, Jun Zhou, Mingjie Wang et al.

This paper focuses on the recently popular task of point cloud completion guided by multimodal information. Although existing methods have achieved excellent performance by fusing auxiliary images, there are still some deficiencies, including the poor generalization ability of the model and insufficient fine-grained semantic information for extracted features. In this work, we propose a novel multimodal fusion network for point cloud completion, which can simultaneously fuse visual and textual information to predict the semantic and geometric characteristics of incomplete shapes effectively. Specifically, to overcome the lack of prior information caused by the small-scale dataset, we employ a pre-trained vision-language model that is trained with a large amount of image-text pairs. Therefore, the textual and visual encoders of this large-scale model have stronger generalization ability. Then, we propose a multi-stage feature fusion strategy to fuse the textual and visual features into the backbone network progressively. Meanwhile, to further explore the effectiveness of fine-grained text descriptions for point cloud completion, we also build a text corpus with fine-grained descriptions, which can provide richer geometric details for 3D shapes. The rich text descriptions can be used for training and evaluating our network. Extensive quantitative and qualitative experiments demonstrate the superior performance of our method compared to state-of-the-art point cloud completion networks.

Xiantong Zhao, Yinan Han, Shengjing Tian et al.

Although recent Siamese network-based trackers have achieved impressive perceptual accuracy for single object tracking in LiDAR point clouds, they usually utilized heavy correlation operations to capture category-level characteristics only, and overlook the inherent merit of arbitrariness in contrast to multiple object tracking. In this work, we propose a radically novel one-stream network with the strength of the instance-level encoding, which avoids the correlation operations occurring in previous Siamese network, thus considerably reducing the computational effort. In particular, the proposed method mainly consists of a Template-aware Transformer Module (TTM) and a Multi-scale Feature Aggregation (MFA) module capable of fusing spatial and semantic information. The TTM stitches the specified template and the search region together and leverages an attention mechanism to establish the information flow, breaking the previous pattern of independent \textit{extraction-and-correlation}. As a result, this module makes it possible to directly generate template-aware features that are suitable for the arbitrary and continuously changing nature of the target, enabling the model to deal with unseen categories. In addition, the MFA is proposed to make spatial and semantic information complementary to each other, which is characterized by reverse directional feature propagation that aggregates information from shallow to deep layers. Extensive experiments on KITTI and nuScenes demonstrate that our method has achieved considerable performance not only for class-specific tracking but also for class-agnostic tracking with less computation and higher efficiency.

Xianheng Ma, Hongchen Tan, Xiuping Liu et al.

In this paper, we leverage the advantages of event cameras to resist harsh lighting conditions, reduce background interference, achieve high time resolution, and protect facial information to study the long-sequence event-based person re-identification (Re-ID) task. To this end, we propose a simple and efficient long-sequence event Re-ID model, namely the Spike-guided Spatiotemporal Semantic Coupling and Expansion Network (S3CE-Net). To better handle asynchronous event data, we build S3CE-Net based on spiking neural networks (SNNs). The S3CE-Net incorporates the Spike-guided Spatial-temporal Attention Mechanism (SSAM) and the Spatiotemporal Feature Sampling Strategy (STFS). The SSAM is designed to carry out semantic interaction and association in both spatial and temporal dimensions, leveraging the capabilities of SNNs. The STFS involves sampling spatial feature subsequences and temporal feature subsequences from the spatiotemporal dimensions, driving the Re-ID model to perceive broader and more robust effective semantics. Notably, the STFS introduces no additional parameters and is only utilized during the training stage. Therefore, S3CE-Net is a low-parameter and high-efficiency model for long-sequence event-based person Re-ID. Extensive experiments have verified that our S3CE-Net achieves outstanding performance on many mainstream long-sequence event-based person Re-ID datasets. Code is available at:https://github.com/Mhsunshine/SC3E_Net.

Yuhao Bian, Shengjing Tian, Xiuping Liu

The widespread deployment of Deep Neural Networks (DNNs) for 3D point cloud processing starkly contrasts with their susceptibility to security breaches, notably backdoor attacks. These attacks hijack DNNs during training, embedding triggers in the data that, once activated, cause the network to make predetermined errors while maintaining normal performance on unaltered data. This vulnerability poses significant risks, especially given the insufficient research on robust defense mechanisms for 3D point cloud networks against such sophisticated threats. Existing attacks either struggle to resist basic point cloud pre-processing methods, or rely on delicate manual design. Exploring simple, effective, imperceptible, and difficult-to-defend triggers in 3D point clouds is still challenging.To address these challenges, we introduce MirrorAttack, a novel effective 3D backdoor attack method, which implants the trigger by simply reconstructing a clean point cloud with an auto-encoder. The data-driven nature of the MirrorAttack obviates the need for complex manual design. Minimizing the reconstruction loss automatically improves imperceptibility. Simultaneously, the reconstruction network endows the trigger with pronounced nonlinearity and sample specificity, rendering traditional preprocessing techniques ineffective in eliminating it. A trigger smoothing module based on spherical harmonic transformation is also attached to regulate the intensity of the attack.Both quantitive and qualitative results verify the effectiveness of our method. We achieve state-of-the-art ASR on different types of victim models with the intervention of defensive techniques. Moreover, the minimal perturbation introduced by our trigger, as assessed by various metrics, attests to the method's stealth, ensuring its imperceptibility.

Juntao Jian, Xiuping Liu, Zixuan Chen et al.

Recent advances in dexterous grasping synthesis have demonstrated significant progress in producing reasonable and plausible grasps for many task purposes. But it remains challenging to generalize to unseen object categories and diverse task instructions. In this paper, we propose G-DexGrasp, a retrieval-augmented generation approach that can produce high-quality dexterous hand configurations for unseen object categories and language-based task instructions. The key is to retrieve generalizable grasping priors, including the fine-grained contact part and the affordance-related distribution of relevant grasping instances, for the following synthesis pipeline. Specifically, the fine-grained contact part and affordance act as generalizable guidance to infer reasonable grasping configurations for unseen objects with a generative model, while the relevant grasping distribution plays as regularization to guarantee the plausibility of synthesized grasps during the subsequent refinement optimization. Our comparison experiments validate the effectiveness of our key designs for generalization and demonstrate the remarkable performance against the existing approaches. Project page: https://g-dexgrasp.github.io/

Jun Zhou, Yaoshun Li, Hongchen Tan et al.

In recent years, point cloud normal estimation, as a classical and foundational algorithm, has garnered extensive attention in the field of 3D geometric processing. Despite the remarkable performance achieved by current Neural Network-based methods, their robustness is still influenced by the quality of training data and the models' performance. In this study, we designed a fundamental framework for normal estimation, enhancing existing model through the incorporation of global information and various constraint mechanisms. Additionally, we employed a confidence-based strategy to select the reasonable samples for fair and robust network training. The introduced sample confidence can be integrated into the loss function to balance the influence of different samples on model training. Finally, we utilized existing orientation methods to correct estimated non-oriented normals, achieving state-of-the-art performance in both oriented and non-oriented tasks. Extensive experimental results demonstrate that our method works well on the widely used benchmarks.

Hongchen Tan, Yi Zhang, Xiuping Liu et al.

As a cutting-edge biosensor, the event camera holds significant potential in the field of computer vision, particularly regarding privacy preservation. However, compared to traditional cameras, event streams often contain noise and possess extremely sparse semantics, posing a formidable challenge for event-based person re-identification (event Re-ID). To address this, we introduce a novel event person re-identification network: the Spectrum-guided Feature Enhancement Network (SFE-Net). This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM). MSAM employs a fourier spectrum transform strategy to filter event noise, while also utilizing an event-guided multi-granularity attention strategy to enhance and capture discriminative person semantics. CPDM employs a consecutive patch dropout strategy to generate multiple incomplete feature maps, encouraging the deep Re-ID model to equally perceive each effective region of the person's body and capture robust person descriptors. Extensive experiments on Event Re-ID datasets demonstrate that our SFE-Net achieves the best performance in this task.

Runduo Han, Xiuping Liu, Shangxuan Yi et al.

In this paper, we proposed a Multi-modal Collaborative Optimization and Expansion Network (MCO-E Net), to use event modalities to resist challenges such as low light, high exposure, and high dynamic range in single-eye expression recognition tasks. The MCO-E Net introduces two innovative designs: Multi-modal Collaborative Optimization Mamba (MCO-Mamba) and Heterogeneous Collaborative and Expansion Mixture-of-Experts (HCE-MoE). MCO-Mamba, building upon Mamba, leverages dual-modal information to jointly optimize the model, facilitating collaborative interaction and fusion of modal semantics. This approach encourages the model to balance the learning of both modalities and harness their respective strengths. HCE-MoE, on the other hand, employs a dynamic routing mechanism to distribute structurally varied experts (deep, attention, and focal), fostering collaborative learning of complementary semantics. This heterogeneous architecture systematically integrates diverse feature extraction paradigms to comprehensively capture expression semantics. Extensive experiments demonstrate that our proposed network achieves competitive performance in the task of single-eye expression recognition, especially under poor lighting conditions.

Xiantong Zhao, Xiuping Liu, Shengjing Tian et al.

3D single object tracking (3DSOT) in LiDAR point clouds is a critical task for outdoor perception, enabling real-time perception of object location, orientation, and motion. Despite the impressive performance of current 3DSOT methods, evaluating them on clean datasets inadequately reflects their comprehensive performance, as the adverse weather conditions in real-world surroundings has not been considered. One of the main obstacles is the lack of adverse weather benchmarks for the evaluation of 3DSOT. To this end, this work proposes a challenging benchmark for LiDAR-based 3DSOT in adverse weather, which comprises two synthetic datasets (KITTI-A and nuScenes-A) and one real-world dataset (CADC-SOT) spanning three weather types: rain, fog, and snow. Based on this benchmark, five representative 3D trackers from different tracking frameworks conducted robustness evaluation, resulting in significant performance degradations. This prompts the question: What are the factors that cause current advanced methods to fail on such adverse weather samples? Consequently, we explore the impacts of adverse weather and answer the above question from three perspectives: 1) target distance; 2) template shape corruption; and 3) target shape corruption. Finally, based on domain randomization and contrastive learning, we designed a dual-branch tracking framework for adverse weather, named DRCT, achieving excellent performance in benchmarks.

Wei Jin, Jun Zhou, Nannan Li et al.

In recent years, deep learning-based point cloud normal estimation has made great progress. However, existing methods mainly rely on the PCPNet dataset, leading to overfitting. In addition, the correlation between point clouds with different noise scales remains unexplored, resulting in poor performance in cross-domain scenarios. In this paper, we explore the consistency of intrinsic features learned from clean and noisy point clouds using an Asymmetric Siamese Network architecture. By applying reasonable constraints between features extracted from different branches, we enhance the quality of normal estimation. Moreover, we introduce a novel multi-view normal estimation dataset that includes a larger variety of shapes with different noise levels. Evaluation of existing methods on this new dataset reveals their inability to adapt to different types of shapes, indicating a degree of overfitting. Extensive experiments show that the proposed dataset poses significant challenges for point cloud normal estimation and that our feature constraint mechanism effectively improves upon existing methods and reduces overfitting in current architectures.

Shengjing Tian, Yinan Han, Xiuping Liu et al.

Single Object Tracking in LiDAR point cloud is one of the most essential parts of environmental perception, in which small objects are inevitable in real-world scenarios and will bring a significant barrier to the accurate location. However, the existing methods concentrate more on exploring universal architectures for common categories and overlook the challenges that small objects have long been thorny due to the relative deficiency of foreground points and a low tolerance for disturbances. To this end, we propose a Siamese network-based method for small object tracking in the LiDAR point cloud, which is composed of the target-awareness prototype mining (TAPM) module and the regional grid subdivision (RGS) module. The TAPM module adopts the reconstruction mechanism of the masked decoder to learn the prototype in the feature space, aiming to highlight the presence of foreground points that will facilitate the subsequent location of small objects. Through the above prototype is capable of accentuating the small object of interest, the positioning deviation in feature maps still leads to high tracking errors. To alleviate this issue, the RGS module is proposed to recover the fine-grained features of the search region based on ViT and pixel shuffle layers. In addition, apart from the normal settings, we elaborately design a scaling experiment to evaluate the robustness of the different trackers on small objects. Extensive experiments on KITTI and nuScenes demonstrate that our method can effectively improve the tracking performance of small targets without affecting normal-sized objects.

Shengjing Tian, Jun Liu, Xiuping Liu

Single object tracking in point clouds has been attracting more and more attention owing to the presence of LiDAR sensors in 3D vision. However, the existing methods based on deep neural networks focus mainly on training different models for different categories, which makes them unable to perform well in real-world applications when encountering classes unseen during the training phase. In this work, we investigate a more challenging task in the LiDAR point clouds, class-agnostic tracking, where a general model is supposed to be learned for any specified targets of both observed and unseen categories. In particular, we first investigate the class-agnostic performances of the state-of-the-art trackers via exposing the unseen categories to them during testing, finding that a key factor for class-agnostic tracking is how to constrain fused features between the template and search region to maintain generalization when the distribution is shifted from observed to unseen classes. Therefore, we propose a feature decorrelation method to address this problem, which eliminates the spurious correlations of the fused features through a set of learned weights and further makes the search region consistent among foreground points and distinctive between foreground and background points. Experiments on the KITTI and NuScenes demonstrate that the proposed method can achieve considerable improvements by benchmarking against the advanced trackers P2B and BAT, especially when tracking unseen objects.

Jun Zhou, Wei Jin, Mingjie Wang et al.

With the burst development of neural networks in recent years, the task of normal estimation has once again become a concern. By introducing the neural networks to classic methods based on problem-specific knowledge, the adaptability of the normal estimation algorithm to noise and scale has been greatly improved. However, the compatibility between neural networks and the traditional methods has not been considered. Similar to the principle of Occam's razor, that is, the simpler is better. We observe that a more simplified process of surface fitting can significantly improve the accuracy of the normal estimation. In this paper, two simple-yet-effective strategies are proposed to address the compatibility between the neural networks and surface fitting process to improve normal estimation. Firstly, a dynamic top-k selection strategy is introduced to better focus on the most critical points of a given patch, and the points selected by our learning method tend to fit a surface by way of a simple tangent plane, which can dramatically improve the normal estimation results of patches with sharp corners or complex patterns. Then, we propose a point update strategy before local surface fitting, which smooths the sharp boundary of the patch to simplify the surface fitting process, significantly reducing the fitting distortion and improving the accuracy of the predicted point normal. The experiments analyze the effectiveness of our proposed strategies and demonstrate that our method achieves SOTA results with the advantage of higher estimation accuracy over most existed approaches.

Jun Zhou, Wei Jin, Mingjie Wang et al.

This paper presents an effective normal estimation method adopting multi-patch stitching for an unstructured point cloud. The majority of learning-based approaches encode a local patch around each point of a whole model and estimate the normals in a point-by-point manner. In contrast, we suggest a more efficient pipeline, in which we introduce a patch-level normal estimation architecture to process a series of overlapping patches. Additionally, a multi-normal selection method based on weights, dubbed as multi-patch stitching, integrates the normals from the overlapping patches. To reduce the adverse effects of sharp corners or noise in a patch, we introduce an adaptive local feature aggregation layer to focus on an anisotropic neighborhood. We then utilize a multi-branch planar experts module to break the mutual influence between underlying piecewise surfaces in a patch. At the stitching stage, we use the learned weights of multi-branch planar experts and distance weights between points to select the best normal from the overlapping parts. Furthermore, we put forward constructing a sparse matrix representation to reduce large-scale retrieval overheads for the loop iterations dramatically. Extensive experiments demonstrate that our method achieves SOTA results with the advantage of lower computational costs and higher robustness to noise over most of the existing approaches.

Hongchen Tan, Xiuping Liu, Baocai Yin et al.

This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM). The MHSAB adaptively captures key local person information, and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and non-key information. Through extensive ablation studies, we verified that the Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM) both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks.

Hongchen Tan, Yuhao Bian, Huasheng Wang et al.

In this paper, we propose a novel person Re-ID model, Consecutive Batch DropBlock Network (CBDB-Net), to capture the attentive and robust person descriptor for the person Re-ID task. The CBDB-Net contains two novel designs: the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL). In the Consecutive Batch DropBlock Module (CBDBM), we firstly conduct uniform partition on the feature maps. And then, we independently and continuously drop each patch from top to bottom on the feature maps, which can output multiple incomplete feature maps. In the training stage, these multiple incomplete features can better encourage the Re-ID model to capture the robust person descriptor for the Re-ID task. In the Elastic Loss (EL), we design a novel weight control item to help the Re-ID model adaptively balance hard sample pairs and easy sample pairs in the whole training process. Through an extensive set of ablation studies, we verify that the Consecutive Batch DropBlock Module (CBDBM) and the Elastic Loss (EL) each contribute to the performance boosts of CBDB-Net. We demonstrate that our CBDB-Net can achieve the competitive performance on the three standard person Re-ID datasets (the Market-1501, the DukeMTMC-Re-ID, and the CUHK03 dataset), three occluded Person Re-ID datasets (the Occluded DukeMTMC, the Partial-REID, and the Partial iLIDS dataset), and a general image retrieval dataset (In-Shop Clothes Retrieval dataset).

Bin Liu, Xiuping Liu, Zhixin Yang et al.

In this paper, we revisit the problem of 3D human modeling from two orthogonal silhouettes of individuals (i.e., front and side views). Different from our prior work, a supervised learning approach based on convolutional neural network (CNN) is investigated to solve the problem by establishing a mapping function that can effectively extract features from two silhouettes and fuse them into coefficients in the shape space of human bodies. A new CNN structure is proposed in our work to exact not only the discriminative features of front and side views and also their mixed features for the mapping function. 3D human models with high accuracy are synthesized from coefficients generated by the mapping function. Existing CNN approaches for 3D human modeling usually learn a large number of parameters (from 8.5M to 355.4M) from two binary images. Differently, we investigate a new network architecture and conduct the samples on silhouettes as input. As a consequence, more accurate models can be generated by our network with only 2.4M coefficients. The training of our network is conducted on samples obtained by augmenting a publicly accessible dataset. Learning transfer by using datasets with a smaller number of scanned models is applied to our network to enable the function of generating results with gender-oriented (or geographical) patterns.

Jun Zhou, Hua Huang, Bin Liu et al.

In this paper, we propose a normal estimation method for unstructured 3D point clouds. In this method, a feature constraint mechanism called Local Plane Features Constraint (LPFC) is used and then a multi-scale selection strategy is introduced. The LPEC can be used in a single-scale point network architecture for a more stable normal estimation of the unstructured 3D point clouds. In particular, it can partly overcome the influence of noise on a large sampling scale compared to the other methods which only use regression loss for normal estimation. For more details, a subnetwork is built after point-wise features extracted layers of the network and it gives more constraints to each point of the local patch via a binary classifier in the end. Then we use multi-task optimization to train the normal estimation and local plane classification tasks simultaneously.Also, to integrate the advantages of multi-scale results, a scale selection strategy is adopted, which is a data-driven approach for selecting the optimal scale around each point and encourages subnetwork specialization. Specifically, we employed a subnetwork called Scale Estimation Network to extract scale weight information from multi-scale features. More analysis is given about the relations between noise levels, local boundary, and scales in the experiment. These relationships can be a better guide to choosing particular scales for a particular model. Besides, the experimental result shows that our network can distinguish the points on the fitting plane accurately and this can be used to guide the normal estimation and our multi-scale method can improve the results well. Compared to some state-of-the-art surface normal estimators, our method is robust to noise and can achieve competitive results.