Zhang Li

Zhang Li, Biao Yang, Qiang Liu et al.

Large Multimodal Models (LMMs) have shown promise in vision-language tasks but struggle with high-resolution input and detailed scene understanding. Addressing these challenges, we introduce Monkey to enhance LMM capabilities. Firstly, Monkey processes input images by dividing them into uniform patches, each matching the size (e.g., 448x448) used in the original training of the well-trained vision encoder. Equipped with individual adapter for each patch, Monkey can handle higher resolutions up to 1344x896 pixels, enabling the detailed capture of complex visual information. Secondly, it employs a multi-level description generation method, enriching the context for scene-object associations. This two-part strategy ensures more effective learning from generated data: the higher resolution allows for a more detailed capture of visuals, which in turn enhances the effectiveness of comprehensive descriptions. Extensive ablative results validate the effectiveness of our designs. Additionally, experiments on 18 datasets further demonstrate that Monkey surpasses existing LMMs in many tasks like Image Captioning and various Visual Question Answering formats. Specially, in qualitative tests focused on dense text question answering, Monkey has exhibited encouraging results compared with GPT4V. Code is available at https://github.com/Yuliang-Liu/Monkey.

Zeyu Yang, Hongye Yang, Zijie Pan et al.

Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene Structure: Existing methods struggle to reveal the spatial and temporal structure of dynamic scenes from directly learning the complex 6D plenoptic function. (ii) Scaling Deformation Modeling: Explicitly modeling scene element deformation becomes impractical for complex dynamics. To address these issues, we consider the spacetime as an entirety and propose to approximate the underlying spatio-temporal 4D volume of a dynamic scene by optimizing a collection of 4D primitives, with explicit geometry and appearance modeling. Learning to optimize the 4D primitives enables us to synthesize novel views at any desired time with our tailored rendering routine. Our model is conceptually simple, consisting of a 4D Gaussian parameterized by anisotropic ellipses that can rotate arbitrarily in space and time, as well as view-dependent and time-evolved appearance represented by the coefficient of 4D spherindrical harmonics. This approach offers simplicity, flexibility for variable-length video and end-to-end training, and efficient real-time rendering, making it suitable for capturing complex dynamic scene motions. Experiments across various benchmarks, including monocular and multi-view scenarios, demonstrate our 4DGS model's superior visual quality and efficiency.

Li Zhang, Yong Liu, Shaoteng Liu et al.

Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing. However, the existing watermarking methods designed for generative models do not take into account the effects of different channels of sample images on watermarking. As a result, the watermarking performance is still limited. To tackle this problem, in this paper, we first analyze the effects of embedding watermark information on different channels. Then, based on the characteristics of human visual system (HVS), we introduce two HVS-based generative model watermarking methods, which are realized in RGB color space and YUV color space respectively. In RGB color space, the watermark is embedded into the R and B channels based on the fact that HVS is more sensitive to G channel. In YUV color space, the watermark is embedded into the DCT domain of U and V channels based on the fact that HVS is more sensitive to brightness changes. Experimental results demonstrate the effectiveness of the proposed work, which improves the fidelity of the model to be protected and has good universality compared with previous methods.

Dongyang Yu, Yunshi Xie, Wangpeng An et al. · meta-ai, tsinghua

We introduce a novel one-stage end-to-end multi-person 2D pose estimation algorithm, known as Joint Coordinate Regression and Association (JCRA), that produces human pose joints and associations without requiring any post-processing. The proposed algorithm is fast, accurate, effective, and simple. The one-stage end-to-end network architecture significantly improves the inference speed of JCRA. Meanwhile, we devised a symmetric network structure for both the encoder and decoder, which ensures high accuracy in identifying keypoints. It follows an architecture that directly outputs part positions via a transformer network, resulting in a significant improvement in performance. Extensive experiments on the MS COCO and CrowdPose benchmarks demonstrate that JCRA outperforms state-of-the-art approaches in both accuracy and efficiency. Moreover, JCRA demonstrates 69.2 mAP and is 78\% faster at inference acceleration than previous state-of-the-art bottom-up algorithms. The code for this algorithm will be publicly available.

Zijie Pan, Jiachen Lu, Xiatian Zhu et al.

High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative models, pretrained on extensive curated web datasets, using knowledge transfer techniques like Score Distillation Sampling (SDS). Efficiently addressing the requirements of high-resolution rendering often necessitates the adoption of latent representation-based models, such as the Latent Diffusion Model (LDM). In this framework, a significant challenge arises: To compute gradients for individual image pixels, it is necessary to backpropagate gradients from the designated latent space through the frozen components of the image model, such as the VAE encoder used within LDM. However, this gradient propagation pathway has never been optimized, remaining uncontrolled during training. We find that the unregulated gradients adversely affect the 3D model's capacity in acquiring texture-related information from the image generative model, leading to poor quality appearance synthesis. To address this overarching challenge, we propose an innovative operation termed Pixel-wise Gradient Clipping (PGC) designed for seamless integration into existing 3D generative models, thereby enhancing their synthesis quality. Specifically, we control the magnitude of stochastic gradients by clipping the pixel-wise gradients efficiently, while preserving crucial texture-related gradient directions. Despite this simplicity and minimal extra cost, extensive experiments demonstrate the efficacy of our PGC in enhancing the performance of existing 3D generative models for high-resolution object rendering.

Yulin Ren, Xin Li, Bingchen Li et al.

We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.

Yanqin Jiang, Li Zhang, Jin Gao et al.

In this paper, we present Consistent4D, a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. Uniquely, we cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need for tedious multi-view data collection and camera calibration. This is achieved by leveraging the object-level 3D-aware image diffusion model as the primary supervision signal for training Dynamic Neural Radiance Fields (DyNeRF). Specifically, we propose a Cascade DyNeRF to facilitate stable convergence and temporal continuity under the supervision signal which is discrete along the time axis. To achieve spatial and temporal consistency, we further introduce an Interpolation-driven Consistency Loss. It is optimized by minimizing the discrepancy between rendered frames from DyNeRF and interpolated frames from a pre-trained video interpolation model. Extensive experiments show that our Consistent4D can perform competitively to prior art alternatives, opening up new possibilities for 4D dynamic object generation from monocular videos, whilst also demonstrating advantage for conventional text-to-3D generation tasks. Our project page is https://consistent4d.github.io/.

Bingchen Li, Xin Li, Yiting Lu et al.

Blind Compressed Image Restoration (CIR) has garnered significant attention due to its practical applications. It aims to mitigate compression artifacts caused by unknown quality factors, particularly with JPEG codecs. Existing works on blind CIR often seek assistance from a quality factor prediction network to facilitate their network to restore compressed images. However, the predicted numerical quality factor lacks spatial information, preventing network adaptability toward image contents. Recent studies in prompt-learning-based image restoration have showcased the potential of prompts to generalize across varied degradation types and degrees. This motivated us to design a prompt-learning-based compressed image restoration network, dubbed PromptCIR, which can effectively restore images from various compress levels. Specifically, PromptCIR exploits prompts to encode compression information implicitly, where prompts directly interact with soft weights generated from image features, thus providing dynamic content-aware and distortion-aware guidance for the restoration process. The light-weight prompts enable our method to adapt to different compression levels, while introducing minimal parameter overhead. Overall, PromptCIR leverages the powerful transformer-based backbone with the dynamic prompt module to proficiently handle blind CIR tasks, winning first place in the NTIRE 2024 challenge of blind compressed image enhancement track. Extensive experiments have validated the effectiveness of our proposed PromptCIR. The code is available at https://github.com/lbc12345/PromptCIR-NTIRE24.

Hao-Yuan Ma, Li Zhang, Shuai Shi

As a deep learning model, Visual Mamba (VMamba) has a low computational complexity and a global receptive field, which has been successful applied to image classification and detection. To extend its applications, we apply VMamba to crowd counting and propose a novel VMambaCC (VMamba Crowd Counting) model. Naturally, VMambaCC inherits the merits of VMamba, or global modeling for images and low computational cost. Additionally, we design a Multi-head High-level Feature (MHF) attention mechanism for VMambaCC. MHF is a new attention mechanism that leverages high-level semantic features to augment low-level semantic features, thereby enhancing spatial feature representation with greater precision. Building upon MHF, we further present a High-level Semantic Supervised Feature Pyramid Network (HS2PFN) that progressively integrates and enhances high-level semantic information with low-level semantic information. Extensive experimental results on five public datasets validate the efficacy of our approach. For example, our method achieves a mean absolute error of 51.87 and a mean squared error of 81.3 on the ShangHaiTech\_PartA dataset. Our code is coming soon.

Li Zhang, Haoxiang Gao, Zhihao Zhang et al.

Referring Video Object Segmentation (RVOS) aims to segment target objects in video sequences based on natural language descriptions. While recent advances in Multi-modal Large Language Models (MLLMs) have improved RVOS performance through enhanced text-video understanding, several challenges remain, including insufficient exploitation of MLLMs' prior knowledge, prohibitive computational and memory costs for long-duration videos, and inadequate handling of complex temporal dynamics. In this work, we propose SVAC, a unified model that improves RVOS by scaling up input frames and segmentation tokens to enhance video-language interaction and segmentation precision. To address the resulting computational challenges, SVAC incorporates the Anchor-Based Spatio-Temporal Compression (ASTC) module to compress visual tokens while preserving essential spatio-temporal structure. Moreover, the Clip-Specific Allocation (CSA) strategy is introduced to better handle dynamic object behaviors across video clips. Experimental results demonstrate that SVAC achieves state-of-the-art performance on multiple RVOS benchmarks with competitive efficiency. Our code is available at https://github.com/lizhang1998/SVAC.

Liang Yin, Xudong Xie, Zhang Li et al.

Scene text retrieval has made significant progress with the assistance of accurate text localization. However, existing approaches typically require costly bounding box annotations for training. Besides, they mostly adopt a customized retrieval strategy but struggle to unify various types of queries to meet diverse retrieval needs. To address these issues, we introduce Muti-query Scene Text retrieval with Attention Recycling (MSTAR), a box-free approach for scene text retrieval. It incorporates progressive vision embedding to dynamically capture the multi-grained representation of texts and harmonizes free-style text queries with style-aware instructions. Additionally, a multi-instance matching module is integrated to enhance vision-language alignment. Furthermore, we build the Multi-Query Text Retrieval (MQTR) dataset, the first benchmark designed to evaluate the multi-query scene text retrieval capability of models, comprising four query types and 16k images. Extensive experiments demonstrate the superiority of our method across seven public datasets and the MQTR dataset. Notably, MSTAR marginally surpasses the previous state-of-the-art model by 6.4% in MAP on Total-Text while eliminating box annotation costs. Moreover, on the MQTR benchmark, MSTAR significantly outperforms the previous models by an average of 8.5%. The code and datasets are available at https://github.com/yingift/MSTAR.

Yuliang Liu, Zhang Li, Mingxin Huang et al.

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks including Text Recognition, Scene Text-Centric Visual Question Answering (VQA), Document-Oriented VQA, Key Information Extraction (KIE), and Handwritten Mathematical Expression Recognition (HMER). To facilitate the assessment of Optical Character Recognition (OCR) capabilities in Large Multimodal Models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression recognition. Most importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal techniques. The evaluation pipeline and benchmark are available at https://github.com/Yuliang-Liu/MultimodalOCR.

Jiahui Zhang, Yurui Chen, Yanpeng Zhou et al.

Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations into models to improve spatial understanding, we aim to unlock the potential of VLMs by leveraging spatially relevant image data. To this end, we introduce a novel 2D spatial data generation and annotation pipeline built upon scene data with 3D ground-truth. This pipeline enables the creation of a diverse set of spatial tasks, ranging from basic perception tasks to more complex reasoning tasks. Leveraging this pipeline, we construct SPAR-7M, a large-scale dataset generated from thousands of scenes across multiple public datasets. In addition, we introduce SPAR-Bench, a benchmark designed to offer a more comprehensive evaluation of spatial capabilities compared to existing spatial benchmarks, supporting both single-view and multi-view inputs. Training on both SPAR-7M and large-scale 2D datasets enables our models to achieve state-of-the-art performance on 2D spatial benchmarks. Further fine-tuning on 3D task-specific datasets yields competitive results, underscoring the effectiveness of our dataset in enhancing spatial reasoning.

Hao-Yuan Ma, Li Zhang, Xiang-Yi Wei

Crowd counting has gained significant popularity due to its practical applications. However, mainstream counting methods ignore precise individual localization and suffer from annotation noise because of counting from estimating density maps. Additionally, they also struggle with high-density images.To address these issues, we propose an end-to-end model called Fine-Grained Extraction Network (FGENet). Different from methods estimating density maps, FGENet directly learns the original coordinate points that represent the precise localization of individuals.This study designs a fusion module, named Fine-Grained Feature Pyramid(FGFP), that is used to fuse feature maps extracted by the backbone of FGENet. The fused features are then passed to both regression and classification heads, where the former provides predicted point coordinates for a given image, and the latter determines the confidence level for each predicted point being an individual. At the end, FGENet establishes correspondences between prediction points and ground truth points by employing the Hungarian algorithm. For training FGENet, we design a robust loss function, named Three-Task Combination (TTC), to mitigate the impact of annotation noise. Extensive experiments are conducted on four widely used crowd counting datasets. Experimental results demonstrate the effectiveness of FGENet. Notably, our method achieves a remarkable improvement of 3.14 points in Mean Absolute Error (MAE) on the ShanghaiTech Part A dataset, showcasing its superiority over the existing state-of-the-art methods. Even more impressively, FGENet surpasses previous benchmarks on the UCF\_CC\_50 dataset with an astounding enhancement of 30.16 points in MAE.

Zeyu Yang, Zijie Pan, Xiatian Zhu et al.

Dynamic 3D scene representation and novel view synthesis are crucial for enabling immersive experiences required by AR/VR and metaverse applications. It is a challenging task due to the complexity of unconstrained real-world scenes and their temporal dynamics. In this paper, we reformulate the reconstruction of a time-varying 3D scene as approximating its underlying spatiotemporal 4D volume by optimizing a collection of native 4D primitives, i.e., 4D Gaussians, with explicit geometry and appearance modeling. Equipped with a tailored rendering pipeline, our representation can be end-to-end optimized using only photometric supervision while free viewpoint viewing at interactive frame rate, making it suitable for representing real world scene with complex dynamic. This approach has been the first solution to achieve real-time rendering of high-resolution, photorealistic novel views for complex dynamic scenes. To facilitate real-world applications, we derive several compact variants that effectively reduce the memory footprint to address its storage bottleneck. Extensive experiments validate the superiority of 4DGS in terms of visual quality and efficiency across a range of dynamic scene-related tasks (e.g., novel view synthesis, 4D generation, scene understanding) and scenarios (e.g., single object, indoor scenes, driving environments, synthetic and real data).

Zeyu Yang, Zijie Pan, Yuankun Yang et al.

Driving view synthesis along free-form trajectories is essential for realistic driving simulations, enabling closed-loop evaluation of end-to-end driving policies. Existing methods excel at view interpolation along recorded paths but struggle to generalize to novel trajectories due to limited viewpoints in driving videos. To tackle this challenge, we propose DriveX, a novel free-form driving view synthesis framework, that progressively distills generative prior into the 3D Gaussian model during its optimization. Within this framework, we utilize a video diffusion model to refine the degraded novel trajectory renderings from the in-training Gaussian model, while the restored videos in turn serve as additional supervision for optimizing the 3D Gaussian. Concretely, we craft an inpainting-based video restoration task, which can disentangle the identification of degraded regions from the generative capability of the diffusion model and remove the need of simulating specific degraded pattern in the training of the diffusion model. To further enhance the consistency and fidelity of generated contents, the pseudo ground truth is progressively updated with gradually improved novel trajectory rendering, allowing both components to co-adapt and reinforce each other while minimizing the disruption on the optimization. By tightly integrating 3D scene representation with generative prior, DriveX achieves high-quality view synthesis beyond recorded trajectories in real time--unlocking new possibilities for flexible and realistic driving simulations on free-form trajectories.

Weiqi Li, Shijie Zhao, Bin Chen et al. · pku

With the advent of virtual reality technology, omnidirectional image (ODI) rescaling techniques are increasingly embraced for reducing transmitted and stored file sizes while preserving high image quality. Despite this progress, current ODI rescaling methods predominantly focus on enhancing the quality of images in equirectangular projection (ERP) format, which overlooks the fact that the content viewed on head mounted displays (HMDs) is actually a rendered viewport instead of an ERP image. In this work, we emphasize that focusing solely on ERP quality results in inferior viewport visual experiences for users. Thus, we propose ResVR, which is the first comprehensive framework for the joint Rescaling and Viewport Rendering of ODIs. ResVR allows obtaining LR ERP images for transmission while rendering high-quality viewports for users to watch on HMDs. In our ResVR, a novel discrete pixel sampling strategy is developed to tackle the complex mapping between the viewport and ERP, enabling end-to-end training of ResVR pipeline. Furthermore, a spherical pixel shape representation technique is innovatively derived from spherical differentiation to significantly improve the visual quality of rendered viewports. Extensive experiments demonstrate that our ResVR outperforms existing methods in viewport rendering tasks across different fields of view, resolutions, and view directions while keeping a low transmission overhead.

Weiqi Li, Shijie Zhao, Chong Mou et al.

As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with content inaccuracies and inconsistencies due to reliance solely on textual inputs. Although recent motion control techniques provide fine-grained control for video generation, directly applying these methods to ODVs often results in spatial distortion and unsatisfactory performance, especially with complex spherical motions. To tackle these challenges, we propose OmniDrag, the first approach enabling both scene- and object-level motion control for accurate, high-quality omnidirectional image-to-video generation. Building on pretrained video diffusion models, we introduce an omnidirectional control module, which is jointly fine-tuned with temporal attention layers to effectively handle complex spherical motion. In addition, we develop a novel spherical motion estimator that accurately extracts motion-control signals and allows users to perform drag-style ODV generation by simply drawing handle and target points. We also present a new dataset, named Move360, addressing the scarcity of ODV data with large scene and object motions. Experiments demonstrate the significant superiority of OmniDrag in achieving holistic scene-level and fine-grained object-level control for ODV generation. The project page is available at https://lwq20020127.github.io/OmniDrag.

Qiaojun Yu, Ce Hao, Xibin Yuan et al.

Manipulating articulated objects with robotic arms is challenging due to the complex kinematic structure, which requires precise part segmentation for efficient manipulation. In this work, we introduce a novel superpoint-based perception method designed to improve part segmentation in 3D point clouds of articulated objects. We propose a learnable, part-aware superpoint generation technique that efficiently groups points based on their geometric and semantic similarities, resulting in clearer part boundaries. Furthermore, by leveraging the segmentation capabilities of the 2D foundation model SAM, we identify the centers of pixel regions and select corresponding superpoints as candidate query points. Integrating a query-based transformer decoder further enhances our method's ability to achieve precise part segmentation. Experimental results on the GAPartNet dataset show that our method outperforms existing state-of-the-art approaches in cross-category part segmentation, achieving AP50 scores of 77.9% for seen categories (4.4% improvement) and $39.3\%$ for unseen categories (11.6% improvement), with superior results in 5 out of 9 part categories for seen objects and outperforming all previous methods across all part categories for unseen objects.

Haochen Jiang, Yueming Xu, Yihan Zeng et al.

3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting advanced tasks like human interaction and visual navigation. Moreover, traditional 3D scene understanding approaches rely on expensive labeled 3D datasets to train a model for a single task with supervision. Thus, geometric reconstruction with zero-shot scene understanding i.e. Open vocabulary 3D Understanding and Reconstruction, is crucial for the future development of mobile robots. In this paper, we propose OpenOcc, a novel framework unifying the 3D scene reconstruction and open vocabulary understanding with neural radiance fields. We model the geometric structure of the scene with occupancy representation and distill the pre-trained open vocabulary model into a 3D language field via volume rendering for zero-shot inference. Furthermore, a novel semantic-aware confidence propagation (SCP) method has been proposed to relieve the issue of language field representation degeneracy caused by inconsistent measurements in distilled features. Experimental results show that our approach achieves competitive performance in 3D scene understanding tasks, especially for small and long-tail objects.

Hongyu An, Xinfeng Zhang, Shijie Zhao et al.

Omnidirectional videos (ODVs) provide an immersive visual experience by capturing the 360° scene. With the rapid advancements in virtual/augmented reality, metaverse, and generative artificial intelligence, the demand for high-quality ODVs is surging. However, ODVs often suffer from low resolution due to their wide field of view and limitations in capturing devices and transmission bandwidth. Although video super-resolution (SR) is a capable video quality enhancement technique, the performance ceiling and practical generalization of existing methods are limited when applied to ODVs due to their unique attributes. To alleviate spatial projection distortions and temporal flickering of ODVs, we propose a Spatio-Temporal Distortion Aware Network (STDAN) with joint spatio-temporal alignment and reconstruction. Specifically, we incorporate a spatio-temporal continuous alignment (STCA) to mitigate discrete geometric artifacts in parallel with temporal alignment. Subsequently, we introduce an interlaced multi-frame reconstruction (IMFR) to enhance temporal consistency. Furthermore, we employ latitude-saliency adaptive (LSA) weights to focus on regions with higher texture complexity and human-watching interest. By exploring a spatio-temporal jointly framework and real-world viewing strategies, STDAN effectively reinforces spatio-temporal coherence on a novel ODV-SR dataset and ensures affordable computational costs. Extensive experimental results demonstrate that STDAN outperforms state-of-the-art methods in improving visual fidelity and dynamic smoothness of ODVs.

Shuheng Ge, Haoyu Xing, Li Zhang et al.

Creating realistic, natural, and lip-readable talking face videos remains a formidable challenge. Previous research primarily concentrated on generating and aligning single-frame images while overlooking the smoothness of frame-to-frame transitions and temporal dependencies. This often compromised visual quality and effects in practical settings, particularly when handling complex facial data and audio content, which frequently led to semantically incongruent visual illusions. Specifically, synthesized videos commonly featured disorganized lip movements, making them difficult to understand and recognize. To overcome these limitations, this paper introduces the application of optical flow to guide facial image generation, enhancing inter-frame continuity and semantic consistency. We propose "OpFlowTalker", a novel approach that utilizes predicted optical flow changes from audio inputs rather than direct image predictions. This method smooths image transitions and aligns changes with semantic content. Moreover, it employs a sequence fusion technique to replace the independent generation of single frames, thus preserving contextual information and maintaining temporal coherence. We also developed an optical flow synchronization module that regulates both full-face and lip movements, optimizing visual synthesis by balancing regional dynamics. Furthermore, we introduce a Visual Text Consistency Score (VTCS) that accurately measures lip-readability in synthesized videos. Extensive empirical evidence validates the effectiveness of our approach.