HLHuaizhong Lin

Huaizhong Lin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huaizhong Lin has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Fast and Robust Deformable 3D Gaussian Splatting

    by Han Jiao, Jiakai Sun, Lei Zhao, Zhanjie Zhang, Wei Xing, Huaizhong Lin

    3D Gaussian Splatting has demonstrated remarkable real-time rendering capabilities and superior visual quality in novel view synthesis for static scenes. Building upon these advantages, researchers have progressively extended 3D Gaussians to dynamic scene reconstruction. Deformation field-based methods have emerged as a promising approach among various techniques. These methods maintain 3D Gaussian attributes in a canonical field and employ the deformation field to transform this field across temporal sequences. Nevertheless, these approaches frequently encounter challenges such as suboptimal rendering speeds, significant dependence on initial point clouds, and vulnerability to local optima in dim scenes. To overcome these limitations, we present FRoG, an efficient and robust framework for high-quality dynamic scene reconstruction. FRoG integrates per-Gaussian embedding with a coarse-to-fine temporal embedding strategy, accelerating rendering through the early fusion of temporal embeddings. Moreover, to enhance robustness against sparse initializations, we introduce a novel depth- and error-guided sampling strategy. This strategy populates the canonical field with new 3D Gaussians at low-deviation initial positions, significantly reducing the optimization burden on the deformation field and improving detail reconstruction in both static and dynamic regions. Furthermore, by modulating opacity variations, we mitigate the local optima problem in dim scenes, improving color fidelity. Comprehensive experimental results validate that our method achieves accelerated rendering speeds while maintaining state-of-the-art visual quality.


  • Open Access

    Dual-Direction Fine-Tuning of Pre-Trained Text-to-Image Models with Attentive Attribution Alignment

    by Xinyu Wang, Junsheng Luan, Wei Xing, Huaizhong Lin, Lei Zhao

    Recent large pre-trained text-to-image models possess massive prior knowledge, which can generate high-quality images with a simple prompt. However, when we need to generate a personalized object with a specific attribution description, namely, an identity V*, it cannot generate images that match the desired identity. Existing personalization methods for text-to-image models have the following three problems: (1) low identity fidelity, (2) low prompt fidelity and (3) low quality. To address the above issues, we propose a dual-direction fine-tuning method that guides the large pre-trained text-to-image model to generate images corresponding to the input prompt. Specifically, we input a class label into a large pre-trained text-to-image model to generate class-generalized images and caption these images using a Bootstrapping Language–Image Pre-training (BLIP) image-captioning model, obtaining class-generalized prompts. The two fine-tuning directions are ID-strengthen and ID-weaken directions. For the ID-strengthen direction, we append up-weighted V* at the beginning of a class-generalized prompt to obtain an ID-strengthen prompt, then we use the reference images of V* and the ID-strengthen prompt to fine-tune the pre-trained model. For the ID-weaken direction, we append down-weighted V*, obtain an ID-weaken prompt, and fine-tune the pre-trained model. In addition, we propose an attentive attribution alignment strategy to align the semantic information of the weighted prompts to the class-generalized prompts. Qualitative and quantitative experiments show that our method improves identity fidelity and prompt fidelity while maintaining high visual quality.

  • Open Access

    CSCGAN: Cross-Space Contrastive Learning for Blind Image Inpainting

    by Sheng Jin, Weijing Zhang, Tianyi Chu, Zhanjie Zhang, Lei Zhao, Wei Xing, Huaizhong Lin, Lixia Chen

    Existing general image inpainting works require the user to customize a mask to indicate the region to be inpainted. However, the mask is often hard to calibrate accurately in real-world applications, e.g., graffiti removal. Blind image inpainting aims to automatically restore the degraded image into the visually reasonable one without a priori mask to indicate the area to be repaired. So far, most proposed blind inpainting methods convert the task into general inpainting by predicting the mask before inpainting. However, these methods are highly dependent on mask prediction results, which may produce inferior inpainting results if the prediction is inaccurate. To address this issue, we propose a two-stage blind inpainting framework with two novel designs: (1) cross-space contrastive learning, to remove the noise in the degraded images and realize the automatic inpainting in the latent space by reducing the distance of the degraded images and the corresponding complete images in the latent space; and (2) mask-aware adversarial training, to minimize the mutual information between the inpainted feature and the noise. Extensive experiments prove that our blind inpainting framework performs better on multiple datasets than the state-of-the-art methods.

  • Open Access

    Relaxing Accurate Initialization for Monocular Dynamic Scene Reconstruction with Gaussian Splatting

    by Xinyu Wang, Jiafu Chen, Wei Xing, Huaizhong Lin, Lei Zhao

    Monocular dynamic scene reconstruction is a challenging task due to the inherent limitation of observing the scene from a single viewpoint at each timestamp, particularly in the presence of object motion and illumination changes. Recent methods combine Gaussian Splatting with deformation modeling to enable fast training and rendering; however, their performance in real-world scenarios strongly depends on accurate point cloud initialization. When such initialization is unavailable and random point clouds are used instead, reconstruction quality degrades significantly. To address this limitation, we propose an optimization strategy that relaxes the requirement for accurate initialization in Gaussian-Splatting-based monocular dynamic scene reconstruction. The scene is first reconstructed under a static assumption using all monocular frames, allowing stable convergence of background regions. Based on reconstruction errors, a subset of Gaussians is then activated as dynamic to model motion and deformation. In addition, an annealing jitter regularization term is introduced to improve robustness to camera pose inaccuracies commonly observed in real-world datasets. Extensive experiments on established benchmarks demonstrate that the proposed method enables stable training from randomly initialized point clouds and achieves reconstruction performance comparable to approaches relying on accurate point cloud initialization.

  • Open Access

    Three-Dimensional Gaussian Style Transfer Method Based on Two-Dimensional Priors and Iterative Optimization

    by Weijing Zhang, Xinyu Wang, Haolin Yin, Wei Xing, Huaizhong Lin, Lixia Chen, Lei Zhao

    To address the limitations of existing optimization-based 3D style transfer methods in terms of visual quality, 3D consistency, and real-time rendering performance, we propose a novel 3D Gaussian scene style transfer method based on 2D priors and iterative optimization. Our approach introduces a progressive training pipeline that alternates between fine-tuning the 3D Gaussian field and updating a set of supervised stylized images. By gradually injecting style information into the 3D scene through iterative refinement, the method effectively preserves the geometric structure and spatial coherence across viewpoints. Furthermore, we incorporated a pre-trained stable diffusion model as a 2D prior to guide the style adaptation of the 3D Gaussian representation. The combination of diffusion priors and differentiable 3D Gaussian rendering enables high-fidelity style transfer while maintaining real-time rendering capability. Extensive experiments demonstrate that our method significantly improves the visual quality and multi-view consistency of 3D stylized scenes, offering an effective and efficient solution for real-time 3D scene stylization.

  • Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model

    by Chen Rao, Guangyuan Li, Zehua Lan, Jiakai Sun, Junsheng Luan, Wei Xing, Lei Zhao, Huaizhong Lin, Jianfeng Dong, Dalong Zhang


  • Open Access

    Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model

    by Chen Rao, Guangyuan Li, Zehua Lan, Jiakai Sun, Junsheng Luan, Wei Xing, Lei Zhao, Huaizhong Lin, Jianfeng Dong, Dalong Zhang

    Current video deblurring methods have limitations in recovering high-frequency information since the regression losses are conservative with high-frequency details. Since Diffusion Models (DMs) have strong capabilities in generating high-frequency details, we consider introducing DMs into the video deblurring task. However, we found that directly applying DMs to the video deblurring task has the following problems: (1) DMs require many iteration steps to generate videos from Gaussian noise, which consumes many computational resources. (2) DMs are easily misled by the blurry artifacts in the video, resulting in irrational content and distortion of the deblurred video. To address the above issues, we propose a novel video deblurring framework VD-Diff that integrates the diffusion model into the Wavelet-Aware Dynamic Transformer (WADT). Specifically, we perform the diffusion model in a highly compact latent space to generate prior features containing high-frequency information that conforms to the ground truth distribution. We design the WADT to preserve and recover the low-frequency information in the video while utilizing the high-frequency information generated by the diffusion model. Extensive experiments show that our proposed VD-Diff outperforms SOTA methods on GoPro, DVD, BSD, and Real-World Video datasets.

  • Open Access

    DuDoINet: Dual-Domain Implicit Network for Multi-Modality MR Image Arbitrary-scale Super-Resolution

    by Guangyuan Li, Wei Xing, Lei Zhao, Zehua Lan, Zhanjie Zhang, Jiakai Sun, Haolin Yin, Huaizhong Lin, Zhijie Lin

    Compared to single-modality magnetic resonance (MR) image super-resolution (SR) methods, multi-modality MR image methods can utilize high-resolution reference modality (e.g., T1 modality) to provide valuable complementary information for low-resolution target modality (e.g., T2 modality) in SR reconstruction, which can further improve the quality of the SR images. Although they have achieved impressive results, these methods still suffer from the following drawbacks: (1) They can only handle fixed integer upsampling factors, such as 2X, 3X, and 4X, and require training and storing corresponding models for each upsampling factor, which is infeasible in clinical practice; (2) They only perform feature extraction and reconstruction in the image domain. However, the aliasing artifacts produced in the image domain are structural and non-local. Therefore, using only the image domain cannot effectively reconstruct high-quality aliasing-free SR images. To address these issues, we develop a brand-new Dual-Domain Implicit Network (DuDoINet) for multi-modality MR image arbitrary-scale SR. Specifically, we propose a dual-domain learning scheme for multi-modality MR image SR, which allows the network to sufficiently exploit the frequency and image domain information in MR images. In addition, we design implicit attention to achieve arbitrary-scale upsampling of MR images, which utilizes a continuously differentiable function that generates pixel values from pixel coordinates. Furthermore, we designed a deformable cross-modality attention mechanism that can adaptively transfer high-frequency details from the T1 to the T2 modality, better integrating valuable complementary information from the T1 modality. Extensive and comprehensive experiments on healthy subjects and patient datasets demonstrate that our DuDoINet outperforms SOTA methods, demonstrating its great potential for clinical practice.


  • Open Access

    Self-Reference Image Super-Resolution via Pre-trained Diffusion Large Model and Window Adjustable Transformer

    by Guangyuan Li, Wei Xing, Lei Zhao, Zehua Lan, Jiakai Sun, Zhanjie Zhang, Quanwei Zhang, Huaizhong Lin, Zhijie Lin

    Currently, reference-based super-resolution (RefSR) techniques leverage high-resolution (HR) reference images to provide useful content and texture information for low-resolution (LR) images during the super-resolution (SR) process. Nevertheless, it is time-consuming, laborious, and even impossible in some cases to find high-quality reference images. To tackle this problem, we propose a brand-new self-reference image super-resolution approach using a pre-trained diffusion large model and a window adjustable transformer, termed DWTrans. Our proposed method does not require explicitly inputting manually acquired reference images during training and inference. Specifically, we feed the degraded LR images into a pre-trained stable diffusion large model to automatically generate corresponding high-quality self-reference (SRef) images that provide valuable high-frequency details for the LR images in the process of SR. To extract valuable high-frequency information in SRef images, we design a window adjustable transformer with both non-adjustable window layer (NWL) and adjustable window layer (AWL). The NWL learns local features from LR images using a dense window, while the AWL acquires global features from the SRef images using a random sparse window. Furthermore, to fully utilize the high-frequency features in the SRef image, we introduce the adaptive deformable fusion module to adaptively fuse the features of the LR and SRef images. Experimental results validate that our proposed DWTrans outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually.


  • Open Access

    SpatialGAN

    by Lei Zhao, Sihuan Lin, Ailin Li, Huaizhong Lin, Wei Xing, Dongming Lu

    The image generation model based on generative adversarial networks has recently received significant attention and can produce diverse, sharp, and realistic images. However, generating high-resolution images has long been a challenge. In this paper, we propose a progressive spatial recursive adversarial expansion model(called SpatialGAN) capable of producing high-quality samples of the natural image. Our approach uses a cascade of convolutional networks to progressively generate images in a part-to-whole fashion. At each level of spatial expansion, a separate image-to-image spatial adversarial expansion network (conditional GAN) is recursively trained based on context image generated by previous GAN or CGAN. Unlike other coarse-to-fine generative methods that constraint on generative process either by multi-scale resolution or by hierarchical feature, the SpatialGAN decomposes image space into multiple subspaces and gradually resolves uncertainties in the local-to-whole generative process. The SpatialGAN greatly stabilizes and speeds up the training, which allows us to produce images of high quality. Based on visual Inception Score and Fréchet Inception Distance, we demonstrate that the quality of images generated by SpatialGAN on several typical datasets is better than that of images generated by GANs without cascading and comparative with the state of art methods with cascading.