论文检索

Tao Liu 0068, Feilong Chen, Shuai Fan 0005, Chenpeng Du, Qi Chen 0009, Xie Chen 0001, Kai Yu 0004

The paper introduces AniTalker, an innovative framework designed to generate lifelike talking faces from a single portrait. Unlike existing models that primarily focus on verbal cues such as lip synchronization and fail to capture the complex dynamics of facial expressions and nonverbal cues, AniTalker employs a universal motion representation. This innovative representation effectively captures a wide range of facial dynamics, including subtle expressions and head movements. AniTalker enhances motion depiction through two self-supervised learning strategies: the first involves reconstructing target video frames from source frames within the same identity to learn subtle motion representations, and the second develops an identity encoder using metric learning while actively minimizing mutual information between the identity and motion encoders. This approach ensures that the motion representation is dynamic and devoid of identity-specific details, significantly reducing the need for labeled data. Additionally, the integration of a diffusion model with a variance adapter allows for the generation of diverse and controllable facial animations. This method not only demonstrates AniTalker's capability to create detailed and realistic facial movements but also underscores its potential in crafting dynamic avatars for real-world applications. Synthetic results can be viewed at https://github.com/X-LANCE/AniTalker.

Hongye Hou, Xuehao Gao, Zhan Liu, Yang Yang 0066

Recovering the complete shape of a 3D object from limited viewpoints plays an important role in 3D vision. Recent point cloud completion methods prefer an encoding-decoding architecture for generating the global structure and local geometry from a set of input point proxies. In this paper, we introduce an innovative completion method aimed at uncovering structural details from input point clouds and maximizing their utility. Specifically, we improve both Encoding and Decoding for this task: (1) Key Context Fusion Encoding extracts and aggregates homologous key context by adaptively increasing the sampling bias towards salient structure and special contour points. (2) Semantic-based Decoding introduces a semantic EdgeConv module to prompt next Transformer decoder, which effectively learns and generates local geometry with semantic correlations from non-nearest neighbors. The experiments are evaluated on several 3D point cloud and 2.5D depth image datasets. Both qualitative and quantitative evaluations demonstrate that our method outperforms previous state-of-the-art methods.

Ruiyang Xia, Dawei Zhou 0004, Decheng Liu, Lin Yuan 0002, Shuodi Wang, Jie Li 0001, Nannan Wang 0001, Xinbo Gao 0001

One of the serious impacts brought by artificial intelligence is the abuse of deepfake techniques. Despite the proliferation of deepfake detection methods aimed at safeguarding the authenticity of media across the Internet, they mainly consider the improvement of detector architecture or the synthesis of forgery samples. The forgery perceptions, including the feature responses and prediction scores for forgery samples, have not been well considered. As a result, the generalization across multiple deepfake techniques always comes with complicated detector structures and expensive training costs. In this paper, we shift the focus to real-time perception analysis in the training process and generalize deepfake detectors through an efficient method dubbed Forgery Perception Guidance (FPG). In particular, after investigating the deficiencies of forgery perceptions, FPG adopts a sample refinement strategy to pertinently train the detector, thereby elevating the generalization efficiently. Moreover, FPG introduces more sample information as explicit optimizations, which makes the detector further adapt the sample diversities. Experiments demonstrate that FPG improves the generality of deepfake detectors with small training costs, minor detector modifications, and the acquirement of real data only. In particular, our approach not only outperforms the state-of-the-art on both the cross-dataset and cross-manipulation evaluation but also surpasses the baseline that needs more than 3× training time.

Mingzhao Yang, Shangchao Su, Bin Li 0015, Xiangyang Xue 0001

In recent years, the attention towards One-Shot Federated Learning (OSFL) has been driven by its capacity to minimize communication. With the development of the diffusion model (DM), several methods employ the DM for OSFL, utilizing model parameters, image features, or textual prompts as mediums to transfer the local client knowledge to the server. However, these mediums often require public datasets or the uniform feature extractor, significantly limiting their practicality. In this paper, we propose FedDEO, a Description-Enhanced One-Shot Federated Learning Method with DMs, offering a novel exploration of utilizing the DM in OSFL. The core idea of our method involves training local descriptions on the clients, serving as the medium to transfer the knowledge of the distributed clients to the server. Firstly, we train local descriptions on the client data to capture the characteristics of client distributions, which are then uploaded to the server. On the server, the descriptions are used as conditions to guide the DM in generating synthetic datasets that comply with the distributions of various clients, enabling the training of the aggregated model. Theoretical analyses and sufficient quantitation and visualization experiments on three large-scale real-world datasets demonstrate that through the training of local descriptions, the server is capable of generating synthetic datasets with high quality and diversity. Consequently, with advantages in communication and privacy protection, the aggregated model outperforms compared FL or diffusion-based OSFL methods and, on some clients, outperforms the performance ceiling of centralized training.

Wulin Xie, Xiaohuan Lu, Yadong Liu, Jiang Long, Bob Zhang 0001, Shuping Zhao, Jie Wen 0001

Multi-view multi-label classification has recently received extensive attention due to its wide-ranging applications across various fields, such as medical imaging and bioinformatics. However, views and labels are usually incomplete in practical scenarios, attributed to the uncertainties in data collection and manual labeling. To cope with this issue, we propose an uncertainty-aware pseudo-labeling and dual graph driven network (UPDGD-Net), which can fully leverage the supervised information of the available labels and feature information of available views. Different from the existing works, we leverage the label matrix to impose dual graph constraints on the embedded features of both view-level and label-level, which enables the method to maintain the inherent structure of the real data during the feature extraction stage. Furthermore, our network incorporates an uncertainty-aware pseudo-labeling strategy to fill the missing labels, which not only addresses the learning issue of incomplete multi-labels but also enables the method to explore more reliable supervised information to guide the network training. Extensive experiments on five datasets demonstrate that our method outperforms other state-of-the-art methods.

Zhengzhong Kuang, Jianan Lu, Chenhui Hong, Haobin Huang, Suguo Zhu, Xiaowei Zhao, Jun Yu 0002, Jianping Fan 0007

The issue of face privacy protection has aroused wide social concern along with the increasing applications of face images. The latest methods focus on achieving a good privacy-utility tradeoff so that the protected results can still be used to support the downstream computer vision tasks. However, they may suffer from limited flexibility in manipulating this tradeoff because the practical requirements may vary under different scenarios. In this paper, we present a novel recurrent latent representation reorganization (LReOrg) framework to deal with the problem. LReOrg relies on two key modules to deal with the privacy-utility tradeoff, where the first one is responsible for anonymizing the privacy sensitive information and the other is responsible for recovering the destroyed useful insensitive information according to user requirements. LReOrg is advantageous in: (a) enabling users to recurrently process fine-grained attributes; (b) providing flexible control over privacy-utility tradeoff by manipulating which attributes to anonymize or preserve using cross-modal keywords; and (c) eliminating the need of data annotations for network training. The experimental results on benchmark datasets have reported the superior ability of our approach for providing flexible protection on facial information.

Zhenhong Sun, Junyan Wang 0001, Zhiyu Tan, Daoyi Dong, Hailan Ma, Hao Li 0030, Dong Gong

Diffusion models have shown remarkable prowess in text-to-image synthesis and editing, yet they often stumble when tasked with interpreting complex prompts that describe multiple entities with specific attributes and interrelations. The generated images often contain inconsistent multi-entity representation (IMR), reflected as inaccurate presentations of the multiple entities and their attributes. Although providing spatial layout guidance improves the multi-entity generation quality in existing works, it is still challenging to handle the leakage attributes and avoid unnatural characteristics. To address the IMR challenge, we first conduct in-depth analyses of the diffusion process and attention operation, revealing that the IMR challenges largely stem from the process of cross-attention mechanisms. According to the analyses, we introduce the entity guidance generation mechanism, which maintains the integrity of the original diffusion model parameters by integrating plug-in networks. Our work advances the stable diffusion model by segmenting comprehensive prompts into distinct entity-specific prompts with bounding boxes, enabling a transition from multi-entity to single-entity generation in cross-attention layers. More importantly, we introduce entity-centric cross-attention layers that focus on individual entities to preserve their uniqueness and accuracy, alongside global entity alignment layers that refine cross-attention maps using multi-entity priors for precise positioning and attribute accuracy. Additionally, a linear attenuation module is integrated to progressively reduce the influence of these layers during inference, preventing oversaturation and preserving generation fidelity. Our comprehensive experiments demonstrate that this entity guidance generation enhances existing text-to-image models in generating detailed, multi-entity images.

Guan Luo, Tian-Xing Xu, Ying-Tian Liu, Xiaoxiong Fan, Fang-Lue Zhang, Song-Hai Zhang

The modeling and manipulation of 3D scenes captured from the real world are pivotal in various applications, attracting growing research interest. While previous works on editing have achieved interesting results through manipulating 3D meshes, they often require accurately reconstructed meshes to perform editing, which limits their application in 3D content generation. To address this gap, we introduce a novel single-image-driven 3D scene editing approach based on 3D Gaussian Splatting, enabling intuitive manipulation via directly editing the content on a 2D image plane. Our method learns to optimize the 3D Gaussians to align with an edited version of the image rendered from a user-specified viewpoint of the original scene. To capture long-range object deformation, we introduce positional loss into the optimization process of 3D Gaussian Splatting and enable gradient propagation through reparameterization. To handle occluded 3D Gaussians when rendering from the specified viewpoint, we build an anchor-based structure and employ a coarse-to-fine optimization strategy capable of handling long-range deformation while maintaining structural stability. Furthermore, we design a novel masking strategy to adaptively identify non-rigid deformation regions for fine-scale modeling. Extensive experiments show the effectiveness of our method in handling geometric details, long-range, and non-rigid deformation, demonstrating superior editing flexibility and quality compared to previous approaches.

Yuan Tang, Xu Han 0016, Xianzhi Li 0001, Qiao Yu 0002, Yixue Hao, Long Hu, Min Chen 0003

Large 2D vision-language models (2D-LLMs) have gained significant attention by bridging Large Language Models (LLMs) with images using a simple projector. Inspired by their success, large 3D point cloud-language models (3D-LLMs) also integrate point clouds into LLMs. However, directly aligning point clouds with LLM requires expensive training costs, typically in hundreds of GPU-hours on A100, which hinders the development of 3D-LLMs. In this paper, we introduce MiniGPT-3D, an efficient and powerful 3D-LLM that achieves multiple SOTA results while training for only 27 hours on one RTX 3090. Specifically, we propose to align 3D point clouds with LLMs using 2D priors from 2D-LLMs, which can leverage the similarity between 2D and 3D visual information. We introduce a novel four-stage training strategy for modality alignment in a cascaded way, and a mixture of query experts module to adaptively aggregate features with high efficiency. Moreover, we utilize parameter-efficient fine-tuning methods LoRA and Norm fine-tuning, resulting in only 47.8M learnable parameters, which is up to 260x fewer than existing methods. Extensive experiments show that MiniGPT-3D achieves SOTA on 3D object classification and captioning tasks, with significantly cheaper training costs. Notably, MiniGPT-3D gains an 8.12 increase on GPT-4 evaluation score for the challenging object captioning task compared to ShapeLLM-13B, while the latter costs 160 total GPU-hours on 8 A800. We are the first to explore the efficient 3D-LLM, offering new insights to the community. Code and weights are available at https://github.com/TangYuan96/MiniGPT-3D.

Yuxin Mao, Xuyang Shen, Jing Zhang 0052, Zhen Qin 0003, Jinxing Zhou, Mochu Xiang, Yiran Zhong, Yuchao Dai

The Text to Audible-Video Generation (TAVG) task involves generating videos with accompanying audio based on text descriptions. Achieving this requires skillful alignment of both audio and video elements. To support research in this field, we have developed a comprehensive Text to Audible-Video Generation Benchmark (TAVGBench), which contains over 1.7 million clips with a total duration of 11.8 thousand hours. We propose an automatic annotation pipeline to ensure each audible video has detailed descriptions for both its audio and video contents. We also introduce the Audio-Visual Harmoni score (AVHScore) to provide a quantitative measure of the alignment between the generated audio and video modalities. Additionally, we present a baseline model for TAVG called TAVDiffusion, which uses a two-stream latent diffusion model to provide a fundamental starting point for further research in this area. We achieve the alignment of audio and video by employing cross-attention and contrastive learning. Through extensive experiments and evaluations on TAVGBench, we demonstrate the effectiveness of our proposed model under both conventional metrics and our proposed metrics. The dataset and code can be found on this page https://npucvr.github.io/TAVGBench/ and on github https://github.com/OpenNLPLab/TAVGBench.

Bo Dong, Pichao Wang, Hao Luo 0004, Fan Wang 0019

Camouflaged instance segmentation is a challenging task due to the various aspects such as color, structure, lighting, etc., of object instances embedded in complex backgrounds. Although the current DETR-based scheme simplifies the pipeline, it suffers from a large number of object queries, leading to many false positive instances. To address this issue, we propose an adaptive query selection mechanism. Our research reveals that a large number of redundant queries scatter the extracted features of the camouflaged instances. To remove these redundant queries with weak correlation, we evaluate the importance of the object query from the perspectives of information entropy and volatility. Moreover, we observed that occlusion and overlapping instances significantly impact the accuracy of the selection mechanism. Therefore, we design a boundary location embedding mechanism that incorporates fake instance boundaries to obtain better location information for more accurate query instance matching. We conducted extensive experiments on two challenging camouflaged instance segmentation datasets, namely COD10K and NC4K, and demonstrated the effectiveness of our proposed model. Compared with the OSFormer, our model significantly improves the performance by 3.8% AP and 5.6% AP with less computational cost, achieving the state-of-the-art of 44.8 AP and 48.1 AP with ResNet-50 on the COD10K and NC4K test-dev sets, respectively.

Mingyang Sun, Qipeng Yan, Zhuoer Liang, Dongliang Kou, Dingkang Yang, Ruisheng Yuan, Xiao Zhao, Mingcheng Li, Lihua Zhang 0002

Reconstructing garments from monocular videos has attracted considerable attention as it provides a convenient and low-cost solution for clothing digitization. In reality, people wear clothing with countless variations and multiple layers. Existing studies attempt to extract garments from a single video. They either behave poorly in generalization due to reliance on limited clothing templates or struggle to handle the intersections of multi-layered clothing leading to the lack of physical plausibility. Besides, there are inevitable and undetectable overlaps for a single video that hinder researchers from modeling complete and intersection-free multi-layered clothing. To address the above limitations, in this paper, we propose a novel method to reconstruct multi-layered clothing from multiple monocular videos sequentially, which surpasses existing work in generalization and robustness against penetration. For each video, neural fields are employed to implicitly represent the clothed body, from which the meshes with frame-consistent structures are explicitly extracted. Next, we implement a template-free method for extracting a single garment by back-projecting the image segmentation labels of different frames onto these meshes. In this way, multiple garments can be obtained from these monocular videos and then aligned to form the whole outfit. However, intersection always occurs due to overlapping deformation in the real world and perceptual errors in monocular videos. To this end, we innovatively introduce a physics-aware module that combines neural fields with a position-based simulation framework to fine-tune the penetrating vertices of garments, ensuring robustly intersection-free. Additionally, we collect a mini dataset with fashionable garments to evaluate the quality of clothing reconstruction comprehensively. We release our code and data at https://github.com/SMY19999/IF-Garments.

Wu Chen, Hehe Fan, Qiuping Jiang, Chao Huang 0008, Yi Yang 0001

Due to the limitation of collection device and unstable scanning process, point cloud data is usually noisy. This noise deforms the underlying structures of point clouds and inevitably affects downstream tasks such as rendering, reconstruction and classification. In this paper, we propose a Cross-stage Cross-coder Adaptive Edge Graph Convolution Network (C2AENet) to denoise point clouds. Our network uses multiple stages to progressively and iteratively denoise points. To improve the effectiveness, we add connections between two stages and between the encoder and decoder, leading to the cross-stage cross-coder architecture. Additionally, existing graph-based point cloud learning methods tend to capture the local structure. They typically construct a semantic graph based on semantic distance, which may ignore Euclidean neighbors and lead to insufficient geometry perception. Therefore, we introduce a geometric graph and adaptively calculate edge attention based on the local and global structural information of the points. This results in a novel graph convolution module that allows the network to capture richer contextual information and focus on more important parts. Extensive experiments demonstrate that the proposed method is competitive compared with other state-of-the-art methods. The code is available at: https://github.com/chenwuwq/C2AENet.

Junyuan Guo, Hao Tang, Teng Wang, Chao Wang 0003

The tasks of view synthesis and decoupling dynamic objects from the static environment for monocular scenes are both long-standing challenges in CV and CG. Most of the previous NeRF-based methods rely on implicit representation, which require additional supervision and training time. Later, various explicit representations like multi-planes or 3D gaussian splatting have been extended and applied to the task of novel view synthesis for dynamic scenes. They introduce an additional time dimension or a deformation field into the original representation to encode dynamics. Due to the effective explicit representations, these methods greatly reduce the time consumption, but still fail to achieve high rendering quality in some scenes, especially for some real scenes. For the latter decoupling problem, previous neural radiation field methods require frequent tuning of the relevant parameters for different scenes, which is very inconvenient for practical use. We consider above problems and propose a new representation of dynamic scenes based on tensor decomposition, which we call R4D-planes. The key to our method is remapping, which compensates for the shortcomings of the plane structure by fusing space-time information and remapping to new indexes. Furthermore, we implement a new decoupling structure, which can efficiently decouple dynamic and static scenes in a self-supervised manner. Experimental results show our method achieves better rendering quality and training efficiency in both view synthesis and decoupling tasks for monocular scenes.

Rui-Chen Zheng, Yang Ai, Zhen-Hua Ling

This paper studies the task of speech reconstruction from ultrasound tongue images and optical lip videos recorded in a silent speaking mode, where people only activate their intra-oral and extra-oral articulators without producing real speech. This task falls under the umbrella of articulatory-to-acoustic (A2A) conversion and may also be referred to as a silent speech interface. To overcome the domain discrepancy between silent and standard vocalized articulation, we introduce a novel pseudo target generation strategy. It integrates the text modality to align with articulatory movements, thereby guiding the generation of pseudo acoustic features for supervised training on speech reconstruction from silent articulation. Furthermore, we propose to employ a denoising diffusion probabilistic model as the fundamental architecture for the A2A conversion task and train the model using a combined training approach with the generated pseudo acoustic features. Experiments show that our proposed method significantly improves the intelligibility and naturalness of the reconstructed speech in the silent speaking mode compared to all baseline methods. Specifically, the word error rate of the reconstructed speech decreases by approximately 5% when measured using an automatic speech recognition engine for intelligibility assessment, and the subjective mean opinion score for naturalness improves by 0.14. Moreover, analytical experiments reveal that the proposed pseudo target generation strategy can generate pseudo acoustic features that synchronize better with articulatory movements than previous strategies. Samples are available at our project page.

Mingjin Zhang, Longyi Li, Wenxuan Shi, Jie Guo 0009, Yunsong Li 0001, Xinbo Gao 0001

Snapshot spectral compressive imaging can capture spectral information across multiple wavelengths in one imaging. The coded aperture snapshot spectral imaging (CASSI) method, aims to recover 3D spectral cubes from 2D measurements. Most existing approaches employ a deep unfolding framework based on Transformer, which alternately address a data subproblem and a prior subproblem. However, these frameworks lack flexibility regarding the sensing matrix and inter-stage interactions. In addition, the quadratic computational complexity of global Transformer and the restricted receptive field of local Transformer impact reconstruction efficiency and accuracy. In this paper, we propose a dynamic deep unfolding network with mamba for compressive spectral imaging, called VmambaSCI. We integrate spatial-spectral information from the sensing matrix into the data module and utilizes spatial adaptive operations in the stage interaction of the prior module. Furthermore, recognizing that the imaging process causes aliasing of spatial and spectral information, we develop a dual-domain scanning mamba (DSMamba), featuring a novel spatial-channel scanning method for enhanced efficiency and accuracy. To our knowledge, VmambaSCI is the first Mamba-based model for compressive spectral imaging. Experimental results on the public databases, CAVE and KAIST, demonstrate the superiority of the proposed VmambaSCI over the state-of-the-art approaches.

Xin Cheng 0018, Hao Wang 0060, Jinwei Wang, Xiangyang Luo 0001, Bin Ma 0003

In Joint Photographic Experts Group (JPEG) image steganalysis and forensics, the quantization step can reveal the history of image operations. Several methods for estimating the quantization step have been proposed by researchers. However, existing algorithms fail to account for robustness, which limits the application of these algorithms. To solve the above problems, we propose a two-stream network structure based on Swin Transformer. The spatial domain features of JPEG images exhibit strong robustness but low accuracy. Conversely, frequency domain features demonstrate high accuracy but weak robustness. Therefore, we design a two-stream network with the multi-scale feature of Swin Transformer to extract spatial domain features with high robustness and frequency domain features with high accuracy, respectively. Furthermore, to adaptively fuse features in both the frequency domain and spatial domain,we design a Spatial-frequency Information Dynamic Fusion (SIDF) module to dynamically allocate weights. Finally, we modify the network from a regression model to a classification model to speed up convergence and improve the accuracy of the algorithm. The experiment results show that the accuracy of the proposed method is higher than 98% on clean images. Meanwhile, in robust environments, the algorithm proposed maintains an average accuracy of over 81%.

Cong Wang 0018, Chengjin Yu, Jie Mu, Wei Wang 0335

While current CNN-based low-light image enhancement (LIE) approaches have achieved significant progress, they often fail to generate better perceptual quality which requires restoring better details and more natural colors. To address these problems, we set a new path, called PercepLIE, by presenting the VQGAN with Multi-luminance Detail Compensation (MDC) and Global Color Adjustment (GCA). Specifically, observed that latent light features of the low-light images are quite different from those captured in normal light, we utilize VQGAN to explore the latent light representation of normal-light images to help the estimation of the low-light and normal-light mapping. Furthermore, we employ Gamma correction with varying Gamma values on the gradient to create multi-luminance details, forming the basis for our MDC module to facilitate better detail estimation. To optimize the colors of low-light input images, we introduce a simple yet effective GCA module that is based on spatially-varying representation between the estimated normal-light images in this module and low-light inputs. By combining the VQGAN with MDC and GCA within a stage-wise training mechanism, our method generates images with finer details and natural colors and achieves favorable performance on both synthetic and real-world datasets in terms of perceptual quality metrics including NIQE, PI, and LPIPS. The source codes will be made available at https://github.com/supersupercong/PercepLIE.

Zheng Wei 0003, Yuzheng Chen, Wai Tong, Xuan Zong, Huamin Qu, Xian Xu, Lik-Hang Lee

In film education, high expenses and limited space significantly challenge teaching synchronized sound recording (SSR). Traditional methods, which emphasize theory with limited practical experience, often fail to bridge the gap between theoretical understanding and practical application. As such, we introduce MetaEcho, an educational virtual reality leveraging the presence theory for teaching SSR. MetaEcho provides realistic simulations of various recording equipment and facilitates communication between learners and instructors, offering an immersive learning experience that closely mirrors actual practices. An evaluation with 24 students demonstrated that MetaEcho surpasses the traditional method in presence, collaboration, usability, realism, comprehensibility, and creativity. Three experts also commented on the benefits of MetaEcho and the opportunities for promoting SSR education in the metaverse era.

Junran Wu, Xueyuan Chen, Shangzhe Li

Graph contrastive learning has achieved great success in pre-training graph neural networks without ground-truth labels. Leading graph contrastive learning follows the classical scheme of contrastive learning, forcing model to identify the essential information from augmented views. However, general augmented views are produced via random corruption or learning, which inevitably leads to semantics alteration. Although domain knowledge guided augmentations alleviate this issue, the generated views are domain specific and undermine the generalization. In this work, motivated by the firm representation ability of sparse model from pruning, we reformulate the problem of graph contrastive learning via contrasting different model versions rather than augmented views. We first theoretically reveal the superiority of model pruning in contrast to data augmentations. In practice, we take original graph as input and dynamically generate a perturbed graph encoder to contrast with the original encoder by pruning its transformation weights. Furthermore, considering the integrity of node embedding in our method, we are capable of developing a local contrastive loss to tackle the hard negative samples that disturb the model training. We extensively validate our method on various benchmarks regarding graph classification via unsupervised and transfer learning. Compared to the state-of-the-art (SOTA) works, better performance can always be obtained by the proposed method.