Yun Cao

Haoran Zhou, Yun Cao, Wenqing Chu et al.

Point cloud completion has become increasingly popular among generation tasks of 3D point clouds, as it is a challenging yet indispensable problem to recover the complete shape of a 3D object from its partial observation. In this paper, we propose a novel SeedFormer to improve the ability of detail preservation and recovery in point cloud completion. Unlike previous methods based on a global feature vector, we introduce a new shape representation, namely Patch Seeds, which not only captures general structures from partial inputs but also preserves regional information of local patterns. Then, by integrating seed features into the generation process, we can recover faithful details for complete point clouds in a coarse-to-fine manner. Moreover, we devise an Upsample Transformer by extending the transformer structure into basic operations of point generators, which effectively incorporates spatial and semantic relationships between neighboring points. Qualitative and quantitative evaluations demonstrate that our method outperforms state-of-the-art completion networks on several benchmark datasets. Our code is available at https://github.com/hrzhou2/seedformer.

Xingyi Li, Jiahui Zhang, Yiheng Li et al.

As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for detection, typically described as frequency-domain artifacts or high-frequency discrepancies. However, the specific and recurring spectral regularities remain insufficiently understood and characterized. In this paper, we systematically analyze the one-dimensional radial log-power spectra of real and generated images. We find that generated images do not necessarily exhibit higher or lower energy across the entire spectrum or high-band range. Instead, their spectra deviate from the power-law decay and show an anomalous uplift in the ultra-high-frequency tail. We term this phenomenon spectral tail uplift. We further attribute this phenomenon to nonlinear harmonic accumulation in trained generative models, suggesting that it can serve as a structural cue across generative architectures. Based on this observation, we propose Spectral Tail Auxiliary Learning (STAL), a frequency-domain auxiliary supervision framework for generalizable AI-generated image detection. STAL transfers spectral-tail cues from a tail-aware frequency teacher to a spatial detector during training, while all frequency-domain modules are discarded at inference time. Consequently, STAL introduces no inference overhead. Extensive experiments on 9 public datasets show that STAL achieves strong generalization and stability across generators, data distributions, and real-world scenarios.

Hao Chen, Jiafu Wu, Ying Jin et al.

Recently, methods like Zero-1-2-3 have focused on single-view based 3D reconstruction and have achieved remarkable success. However, their predictions for unseen areas heavily rely on the inductive bias of large-scale pretrained diffusion models. Although subsequent work, such as DreamComposer, attempts to make predictions more controllable by incorporating additional views, the results remain unrealistic due to feature entanglement in the vanilla latent space, including factors such as lighting, material, and structure. To address these issues, we introduce the Visual Isotropy 3D Reconstruction Model (VI3DRM), a diffusion-based sparse views 3D reconstruction model that operates within an ID consistent and perspective-disentangled 3D latent space. By facilitating the disentanglement of semantic information, color, material properties and lighting, VI3DRM is capable of generating highly realistic images that are indistinguishable from real photographs. By leveraging both real and synthesized images, our approach enables the accurate construction of pointmaps, ultimately producing finely textured meshes or point clouds. On the NVS task, tested on the GSO dataset, VI3DRM significantly outperforms state-of-the-art method DreamComposer, achieving a PSNR of 38.61, an SSIM of 0.929, and an LPIPS of 0.027. Code will be made available upon publication.

Yuqi Qian, Yun Cao, Haocheng Fu et al.

Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introduced new challenges in intellectual property protection and content provenance. Image watermarking offers a solution to these challenges, and recent work has increasingly explored Noise-as-Watermark (NaW) approaches that integrate watermarking directly into the diffusion process. However, existing NaW methods fail to balance robustness and diversity. We attribute this weakness to value encoding, which encodes watermark bits into individual sampled values. It is extremely fragile in practical application scenarios. To address this, we encode watermark bits into the structured noise pattern, so that the watermark is preserved even when individual values are perturbed. To further ensure generation diversity, we introduce a dedicated randomization design that reshuffles the positions of noise elements without changing their values, preventing the watermark from inducing fixed noise patterns or spatial locations. Extensive experiments demonstrate that our method achieves state-of-the-art robustness while maintaining high generation quality across a wide range of lossy scenarios.

Yuqi Pang, Bowen Yang, Haoqin Tu et al.

Although Large Language Models (LLMs) excel in reasoning and generation for language tasks, they are not specifically designed for multimodal challenges. Training Multimodal Large Language Models (MLLMs), however, is resource-intensive and constrained by various training limitations. In this paper, we propose the Modular-based Visual Contrastive Decoding (MVCD) framework to move this obstacle. Our framework leverages LLMs' In-Context Learning (ICL) capability and the proposed visual contrastive-example decoding (CED), specifically tailored for this framework, without requiring any additional training. By converting visual signals into text and focusing on contrastive output distributions during decoding, we can highlight the new information introduced by contextual examples, explore their connections, and avoid over-reliance on prior encoded knowledge. MVCD enhances LLMs' visual perception to make it see and reason over the input visuals. To demonstrate MVCD's effectiveness, we conduct experiments with four LLMs across five question answering datasets. Our results not only show consistent improvement in model accuracy but well explain the effective components inside our decoding strategy. Our code will be available at https://github.com/Pbhgit/MVCD.

Pengfei Pei, Xianfeng Zhao, Yun Cao et al.

In recent years, the spread of fake videos has brought great influence on individuals and even countries. It is important to provide robust and reliable results for fake videos. The results of conventional detection methods are not reliable and not robust for unseen videos. Another alternative and more effective way is to find the original video of the fake video. For example, fake videos from the Russia-Ukraine war and the Hong Kong law revision storm are refuted by finding the original video. We use an improved retrieval method to find the original video, named ViTHash. Specifically, tracing the source of fake videos requires finding the unique one, which is difficult when there are only small differences in the original videos. To solve the above problems, we designed a novel loss Hash Triplet Loss. In addition, we designed a tool called Localizator to compare the difference between the original traced video and the fake video. We have done extensive experiments on FaceForensics++, Celeb-DF and DeepFakeDetection, and we also have done additional experiments on our built three datasets: DAVIS2016-TL (video inpainting), VSTL (video splicing) and DFTL (similar videos). Experiments have shown that our performance is better than state-of-the-art methods, especially in cross-dataset mode. Experiments also demonstrated that ViTHash is effective in various forgery detection: video inpainting, video splicing and deepfakes. Our code and datasets have been released on GitHub: \url{https://github.com/lajlksdf/vtl}.

Yanjie Pan, Qingdong He, Zhengkai Jiang et al.

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously preserving semantic fidelity across multiple heterogeneous control signals while maintaining high visual quality, where they employ separate control branches that often introduce conflicting guidance during the denoising process, leading to structural distortions and artifacts in generated images. To address this issue, we present PixelPonder, a novel unified control framework, which allows for effective control of multiple visual conditions under a single control structure. Specifically, we design a patch-level adaptive condition selection mechanism that dynamically prioritizes spatially relevant control signals at the sub-region level, enabling precise local guidance without global interference. Additionally, a time-aware control injection scheme is deployed to modulate condition influence according to denoising timesteps, progressively transitioning from structural preservation to texture refinement and fully utilizing the control information from different categories to promote more harmonious image generation. Extensive experiments demonstrate that PixelPonder surpasses previous methods across different benchmark datasets, showing superior improvement in spatial alignment accuracy while maintaining high textual semantic consistency.

Yiran He, Yun Cao, Bowen Yang et al.

The rapid development of generative AI facilitates content creation and makes image manipulation easier and more difficult to detect. While multimodal Large Language Models (LLMs) have encoded rich world knowledge, they are not inherently tailored for combating AI-generated Content (AIGC) and struggle to comprehend local forgery details. In this work, we investigate the application of multimodal LLMs in forgery detection. We propose a framework capable of evaluating image authenticity, localizing tampered regions, providing evidence, and tracing generation methods based on semantic tampering clues. Our method demonstrates that the potential of LLMs in forgery analysis can be effectively unlocked through meticulous prompt engineering and the application of few-shot learning techniques. We conduct qualitative and quantitative experiments and show that GPT4V can achieve an accuracy of 92.1% in Autosplice and 86.3% in LaMa, which is competitive with state-of-the-art AIGC detection methods. We further discuss the limitations of multimodal LLMs in such tasks and propose potential improvements.

Yanxiao Sun, Jiafu Wu, Yun Cao et al. · tencent-ai

Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based on trajectory-preserving or distribution-matching have been developed to accelerate video generation models, these approaches often suffer from performance breakdown or increased artifacts under few-step settings. To address these limitations, we propose \textbf{\emph{SwiftVideo}}, a unified and stable distillation framework that combines the advantages of trajectory-preserving and distribution-matching strategies. Our approach introduces continuous-time consistency distillation to ensure precise preservation of ODE trajectories. Subsequently, we propose a dual-perspective alignment that includes distribution alignment between synthetic and real data along with trajectory alignment across different inference steps. Our method maintains high-quality video generation while substantially reducing the number of inference steps. Quantitative evaluations on the OpenVid-1M benchmark demonstrate that our method significantly outperforms existing approaches in few-step video generation.

Bowen Yang, Yun Cao, Chen He et al.

Text-to-video retrieval requires precise alignment between language and temporally rich audio-video signals. However, existing methods often emphasize visual cues while underutilizing audio semantics or relying on coarse fusion strategies, resulting in suboptimal multimodal representations. We introduce GAIS, a retrieval framework that strengthens multimodal alignment from both representation and regularization perspectives. First, a Frame-level Gated Fusion (FGF) module adaptively integrates audio-visual features under textual guidance, enabling fine-grained temporal selection of informative frames. Second, a Semantic Variance-Scaled Perturbation (SVSP) mechanism regularizes the text embedding space by controlling perturbation magnitude in a semantics-aware manner. These two modules are complementary: FGF minimizes modality gaps through selective fusion, while SVSP improves embedding stability and discrimination. Extensive experiments on MSR-VTT, DiDeMo, LSMDC, and VATEX demonstrate that GAIS consistently outperforms strong baselines across multiple retrieval metrics while maintaining notable computational efficiency.

Yuqi Pang, Bowen Yang, Yun Cao et al.

Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and inference costs, as well as challenges in extracting visual details, effectively bridging across modalities. In this work, we propose a novel visual framework, MoCHA, to address these issues. Our framework integrates four vision backbones (i.e., CLIP, SigLIP, DINOv2 and ConvNeXt) to extract complementary visual features and is equipped with a sparse Mixture of Experts Connectors (MoECs) module to dynamically select experts tailored to different visual dimensions. To mitigate redundant or insufficient use of the visual information encoded by the MoECs module, we further design a Hierarchical Group Attention (HGA) with intra- and inter-group operations and an adaptive gating strategy for encoded visual features. We train MoCHA on two mainstream LLMs (e.g., Phi2-2.7B and Vicuna-7B) and evaluate their performance across various benchmarks. Notably, MoCHA outperforms state-of-the-art open-weight models on various tasks. For example, compared to CuMo (Mistral-7B), our MoCHA (Phi2-2.7B) presents outstanding abilities to mitigate hallucination by showing improvements of 3.25% in POPE and to follow visual instructions by raising 153 points on MME. Finally, ablation studies further confirm the effectiveness and robustness of the proposed MoECs and HGA in improving the overall performance of MoCHA.

Jiafu Wu, Yabiao Wang, Jian Li et al.

Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture. Conventionally, DiTs are constructed by stacking serial isotropic global modeling transformers, which face significant quadratic computational cost. However, through empirical analysis, we find that DiTs do not rely as heavily on global information as previously believed. In fact, most layers exhibit significant redundancy in global computation. Additionally, conventional attention mechanisms suffer from low-frequency inertia, limiting their efficiency. To address these issues, we propose Pseudo Shifted Window Attention (PSWA), which fundamentally mitigates global attention redundancy. PSWA achieves moderate global-local information through window attention. It further utilizes a high-frequency bridging branch to simulate shifted window operations, which both enrich the high-frequency information and strengthen inter-window connections. Furthermore, we propose the Progressive Coverage Channel Allocation (PCCA) strategy that captures high-order attention without additional computational cost. Based on these innovations, we propose a series of Pseudo Progressive Diffusion Transformer (PiT). Our extensive experiments show their superior performance; for example, our proposed PiT-L achieves 54% FID improvement over DiT-XL/2 while using less computation.

Kangwei Liu, Junwu Liu, Xiaowei Yi et al.

Audio-driven emotional 3D facial animation encounters two significant challenges: (1) reliance on single-modal control signals (videos, text, or emotion labels) without leveraging their complementary strengths for comprehensive emotion manipulation, and (2) deterministic regression-based mapping that constrains the stochastic nature of emotional expressions and non-verbal behaviors, limiting the expressiveness of synthesized animations. To address these challenges, we present a diffusion-based framework for controllable expressive 3D facial animation. Our approach introduces two key innovations: (1) a FLAME-centered multimodal emotion binding strategy that aligns diverse modalities (text, audio, and emotion labels) through contrastive learning, enabling flexible emotion control from multiple signal sources, and (2) an attention-based latent diffusion model with content-aware attention and emotion-guided layers, which enriches motion diversity while maintaining temporal coherence and natural facial dynamics. Extensive experiments demonstrate that our method outperforms existing approaches across most metrics, achieving a 21.6\% improvement in emotion similarity while preserving physiologically plausible facial dynamics. Project Page: https://kangweiiliu.github.io/Control_3D_Animation.

Kangwei Liu, Junwu Liu, Yun Cao et al.

Recent advances in talking face generation have significantly improved facial animation synthesis. However, existing approaches face fundamental limitations: 3DMM-based methods maintain temporal consistency but lack fine-grained regional control, while Stable Diffusion-based methods enable spatial manipulation but suffer from temporal inconsistencies. The integration of these approaches is hindered by incompatible control mechanisms and semantic entanglement of facial representations. This paper presents DisentTalk, introducing a data-driven semantic disentanglement framework that decomposes 3DMM expression parameters into meaningful subspaces for fine-grained facial control. Building upon this disentangled representation, we develop a hierarchical latent diffusion architecture that operates in 3DMM parameter space, integrating region-aware attention mechanisms to ensure both spatial precision and temporal coherence. To address the scarcity of high-quality Chinese training data, we introduce CHDTF, a Chinese high-definition talking face dataset. Extensive experiments show superior performance over existing methods across multiple metrics, including lip synchronization, expression quality, and temporal consistency. Project Page: https://kangweiiliu.github.io/DisentTalk.

Guangpin Tao, Xiaozhong Ji, Wenzhuo Wang et al.

Deep-learning based Super-Resolution (SR) methods have exhibited promising performance under non-blind setting where blur kernel is known. However, blur kernels of Low-Resolution (LR) images in different practical applications are usually unknown. It may lead to significant performance drop when degradation process of training images deviates from that of real images. In this paper, we propose a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain. To our best knowledge, this is the first deep learning method which conducts blur kernel estimation in frequency domain. Specifically, we first demonstrate that feature representation in frequency domain is more conducive for blur kernel reconstruction than in spatial domain. Next, we present a Spectrum-to-Kernel (S$2$K) network to estimate general blur kernels in diverse forms. We use a Conditional GAN (CGAN) combined with SR-oriented optimization target to learn the end-to-end translation from degraded images' spectra to unknown kernels. Extensive experiments on both synthetic and real-world images demonstrate that our proposed method sufficiently reduces blur kernel estimation error, thus enables the off-the-shelf non-blind SR methods to work under blind setting effectively, and achieves superior performance over state-of-the-art blind SR methods, averagely by 1.39dB, 0.48dB on commom blind SR setting (with Gaussian kernels) for scales $2\times$ and $4\times$, respectively.

Xiaozhong Ji, Guangpin Tao, Yun Cao et al.

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal degradation (e.g., bicubic down-sampling) deviate from real source domain. The domain gap between the LR images and the real-world images can be observed clearly on frequency density, which inspires us to explictly narrow the undesired gap caused by incorrect degradation. From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding LR images. To provide useful gradient information for kernel estimation, we propose Frequency Density Comparator (FDC) by distinguishing the frequency density of images on different scales. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models. Extensive experiments show that the proposed FCA improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception, thus providing a novel effective framework for real-world SR application.

Yun Cao, Yuebin Wang, Junhuan Peng et al.

With a small number of labeled samples for training, it can save considerable manpower and material resources, especially when the amount of high spatial resolution remote sensing images (HSR-RSIs) increases considerably. However, many deep models face the problem of overfitting when using a small number of labeled samples. This might degrade HSRRSI retrieval accuracy. Aiming at obtaining more accurate HSR-RSI retrieval performance with small training samples, we develop a deep metric learning approach with generative adversarial network regularization (DML-GANR) for HSR-RSI retrieval. The DML-GANR starts from a high-level feature extraction (HFE) to extract high-level features, which includes convolutional layers and fully connected (FC) layers. Each of the FC layers is constructed by deep metric learning (DML) to maximize the interclass variations and minimize the intraclass variations. The generative adversarial network (GAN) is adopted to mitigate the overfitting problem and validate the qualities of extracted high-level features. DML-GANR is optimized through a customized approach, and the optimal parameters are obtained. The experimental results on the three data sets demonstrate the superior performance of DML-GANR over state-of-the-art techniques in HSR-RSI retrieval.

Yun Cao, Jie Mei, Yuebin Wang et al.

Subspace learning (SL) plays an important role in hyperspectral image (HSI) classification, since it can provide an effective solution to reduce the redundant information in the image pixels of HSIs. Previous works about SL aim to improve the accuracy of HSI recognition. Using a large number of labeled samples, related methods can train the parameters of the proposed solutions to obtain better representations of HSI pixels. However, the data instances may not be sufficient enough to learn a precise model for HSI classification in real applications. Moreover, it is well-known that it takes much time, labor and human expertise to label HSI images. To avoid the aforementioned problems, a novel SL method that includes the probability assumption called subspace learning with conditional random field (SLCRF) is developed. In SLCRF, first, the 3D convolutional autoencoder (3DCAE) is introduced to remove the redundant information in HSI pixels. In addition, the relationships are also constructed using the spectral-spatial information among the adjacent pixels. Then, the conditional random field (CRF) framework can be constructed and further embedded into the HSI SL procedure with the semi-supervised approach. Through the linearized alternating direction method termed LADMAP, the objective function of SLCRF is optimized using a defined iterative algorithm. The proposed method is comprehensively evaluated using the challenging public HSI datasets. We can achieve stateof-the-art performance using these HSI sets.

Andreas Lugmayr, Martin Danelljan, Radu Timofte et al.

This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. For training, only one set of source input images is therefore provided along with a set of unpaired high-quality target images. In Track 1: Image Processing artifacts, the aim is to super-resolve images with synthetically generated image processing artifacts. This allows for quantitative benchmarking of the approaches \wrt a ground-truth image. In Track 2: Smartphone Images, real low-quality smart phone images have to be super-resolved. In both tracks, the ultimate goal is to achieve the best perceptual quality, evaluated using a human study. This is the second challenge on the subject, following AIM 2019, targeting to advance the state-of-the-art in super-resolution. To measure the performance we use the benchmark protocol from AIM 2019. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.

Yaqi Liu, Xianfeng Zhao, Xiaobin Zhu et al.

Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the other. In this paper, we propose a novel adversarial learning framework to train the deep matching network for CISDL. Our framework mainly consists of three building blocks: 1) the deep matching network based on atrous convolution (DMAC) aims to generate two high-quality candidate masks which indicate the suspected regions of the two input images, 2) the detection network is designed to rectify inconsistencies between the two corresponding candidate masks, 3) the discriminative network drives the DMAC network to produce masks that are hard to distinguish from ground-truth ones. In DMAC, atrous convolution is adopted to extract features with rich spatial information, the correlation layer based on the skip architecture is proposed to capture hierarchical features, and atrous spatial pyramid pooling is constructed to localize tampered regions at multiple scales. The detection network and the discriminative network act as the losses with auxiliary parameters to supervise the training of DMAC in an adversarial way. Extensive experiments, conducted on 21 generated testing sets and two public datasets, demonstrate the effectiveness of the proposed framework and the superior performance of DMAC.

Yaqi Liu, Qingxiao Guan, Xianfeng Zhao et al.

In this paper, we propose to utilize Convolutional Neural Networks (CNNs) and the segmentation-based multi-scale analysis to locate tampered areas in digital images. First, to deal with color input sliding windows of different scales, a unified CNN architecture is designed. Then, we elaborately design the training procedures of CNNs on sampled training patches. With a set of robust multi-scale tampering detectors based on CNNs, complementary tampering possibility maps can be generated. Last but not least, a segmentation-based method is proposed to fuse the maps and generate the final decision map. By exploiting the benefits of both the small-scale and large-scale analyses, the segmentation-based multi-scale analysis can lead to a performance leap in forgery localization of CNNs. Numerous experiments are conducted to demonstrate the effectiveness and efficiency of our method.

Yun Cao, Zhiming Zhou, Weinan Zhang et al.

Colorization of grayscale images has been a hot topic in computer vision. Previous research mainly focuses on producing a colored image to match the original one. However, since many colors share the same gray value, an input grayscale image could be diversely colored while maintaining its reality. In this paper, we design a novel solution for unsupervised diverse colorization. Specifically, we leverage conditional generative adversarial networks to model the distribution of real-world item colors, in which we develop a fully convolutional generator with multi-layer noise to enhance diversity, with multi-layer condition concatenation to maintain reality, and with stride 1 to keep spatial information. With such a novel network architecture, the model yields highly competitive performance on the open LSUN bedroom dataset. The Turing test of 80 humans further indicates our generated color schemes are highly convincible.