arXiv subjects

Guixu Zhang

Publications and source records attributed to Guixu Zhang.

At least 19 recordsLinked to original sources

arXiv2026

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs

Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence for language modeling. Most existing resamplers adopt a single, fixed aggregation scope via global cross-attention, which can blur fine-grained local evidence and limit the ability to capture both local details and global context within a fixed token budget. In this work, we propose MS-Resampler, a multi-scope visual resampling framework for MLLMs. MS-Resampler instantiates multiple scope-specific resamplers by injecting explicit spatial scope priors into the resampling attention, enabling each branch to aggregate visual information at a particular granularity from local to global. The outputs of these scope-specific resamplers are then adaptively fused to produce the final visual representations for language modeling. Extensive experiments on ten public multimodal benchmarks show that MS-Resampler consistently improves visual understanding and multimodal reasoning over conventional single-scope resamplers, while introducing only minimal computational overhead.

cs.CV↗

arXiv2026

CSD: Content-aware Speculative Decoding for Efficient Image Generation

Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of low acceptance rates, and directly relaxing its criteria leads to degradation in image quality. In this paper, we propose a novel content-aware speculative decoding algorithm, termed CSD, which integrates an entropy-based probability relaxation mechanism with an optimal resampling strategy to enhance the inference efficiency for autoregressive image generation. By leveraging the informational uncertainty inherent in different regions of an image, CSD dynamically adjusts the acceptance probability of candidate tokens, increasing the acceptance rate in low-detail areas to accelerate generation. Moreover, a distribution alignment filter is introduced to ensure the output distribution to be aligned with the target model, which significantly improves the generative quality. Experiments conducted on Lumina-mGPT and Janus-Pro demonstrate that the superiority of the proposed CSD. Our source code is available at https://github.com/aderfebr/CSD.

cs.CV↗

arXiv2026

QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression

Multimodal large language models suffer from severe computational and memory bottlenecks, as the number of visual tokens far exceeds that of textual tokens. While recent methods employ projector modules to align and compress visual tokens into text-aligned features, they typically depend on fixed heuristics that limit adaptability across diverse scenarios. In this paper, we first propose Query Guided Mixture-of-Projector (QMoP), a novel and flexible framework that adaptively compresses visual tokens via three collaborative branches: (1) a pooling-based branch for coarse-grained global semantics, (2) a resampler branch for extracting high-level semantic representations, and (3) a pruning-based branch for fine-grained token selection to preserve critical visual detail. To adaptively coordinate these branches, we introduce the Query Guided Router (QGR), which dynamically selects and weights the outputs from different branches based on both visual input and textual queries. A Mixture-of-Experts-style fusion mechanism is designed to aggregate the outputs, harnessing the strengths of each strategy while suppressing noise. To systematically evaluate the effects of Visual Token Compression, we also develop VTCBench, a dedicated benchmark for evaluating the information loss induced by visual token compression. Extensive experiments demonstrate that despite relying on fundamental compression modules, QMoP outperforms strong baselines and delivers significant savings in memory, computation, and inference time.

cs.CV↗

arXiv2026

Frequency Error-Guided Under-sampling Optimization for Multi-Contrast MRI Reconstruction

Magnetic resonance imaging (MRI) plays a vital role in clinical diagnostics, yet it remains hindered by long acquisition times and motion artifacts. Multi-contrast MRI reconstruction has emerged as a promising direction by leveraging complementary information from fully-sampled reference scans. However, existing approaches suffer from three major limitations: (1) superficial reference fusion strategies, such as simple concatenation, (2) insufficient utilization of the complementary information provided by the reference contrast, and (3) fixed under-sampling patterns. We propose an efficient and interpretable frequency error-guided reconstruction framework to tackle these issues. We first employ a conditional diffusion model to learn a Frequency Error Prior (FEP), which is then incorporated into a unified framework for jointly optimizing both the under-sampling pattern and the reconstruction network. The proposed reconstruction model employs a model-driven deep unfolding framework that jointly exploits frequency- and image-domain information. In addition, a spatial alignment module and a reference feature decomposition strategy are incorporated to improve reconstruction quality and bridge model-based optimization with data-driven learning for improved physical interpretability. Comprehensive validation across multiple imaging modalities, acceleration rates (4-30x), and sampling schemes demonstrates consistent superiority over state-of-the-art methods in both quantitative metrics and visual quality. All codes are available at https://github.com/fangxinming/JUF-MRI.

cs.CV↗

arXiv2025

Mamba-Based Modality Disentanglement Network for Multi-Contrast MRI Reconstruction

Magnetic resonance imaging (MRI) is a cornerstone of modern clinical diagnosis, offering unparalleled soft-tissue contrast without ionizing radiation. However, prolonged scan times remain a major barrier to patient throughput and comfort. Existing accelerated MRI techniques often struggle with two key challenges: (1) failure to effectively utilize inherent K-space prior information, leading to persistent aliasing artifacts from zero-filled inputs; and (2) contamination of target reconstruction quality by irrelevant information when employing multi-contrast fusion strategies. To overcome these challenges, we present MambaMDN, a dual-domain framework for multi-contrast MRI reconstruction. Our approach first employs fully-sampled reference K-space data to complete the undersampled target data, generating structurally aligned but modality-mixed inputs. Subsequently, we develop a Mamba-based modality disentanglement network to extract and remove reference-specific features from the mixed representation. Furthermore, we introduce an iterative refinement mechanism to progressively enhance reconstruction accuracy through repeated feature purification. Extensive experiments demonstrate that MambaMDN can significantly outperform existing multi-contrast reconstruction methods.

cs.CV↗

arXiv2025

First-order State Space Model for Lightweight Image Super-resolution

State space models (SSMs), particularly Mamba, have shown promise in NLP tasks and are increasingly applied to vision tasks. However, most Mamba-based vision models focus on network architecture and scan paths, with little attention to the SSM module. In order to explore the potential of SSMs, we modified the calculation process of SSM without increasing the number of parameters to improve the performance on lightweight super-resolution tasks. In this paper, we introduce the First-order State Space Model (FSSM) to improve the original Mamba module, enhancing performance by incorporating token correlations. We apply a first-order hold condition in SSMs, derive the new discretized form, and analyzed cumulative error. Extensive experimental results demonstrate that FSSM improves the performance of MambaIR on five benchmark datasets without additionally increasing the number of parameters, and surpasses current lightweight SR methods, achieving state-of-the-art results.

cs.CV↗

arXiv2025

Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling

Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view, where multiple plausible depth configurations can produce identical 2D projections. In this paper, we present a novel depth estimation method that combines both local and global cues to improve prediction accuracy. Specifically, we propose the Gated Large Kernel Attention Module (GLKAM) to effectively capture multi-scale local structural information by leveraging large kernel convolutions with a gated mechanism. To further enhance the global perception of the network, we introduce the Global Bin Prediction Module (GBPM), which estimates the global distribution of depth bins and provides structural guidance for depth regression. Extensive experiments on the NYU-V2 and KITTI dataset demonstrate that our method achieves competitive performance and outperforms existing approaches, validating the effectiveness of each proposed component.

cs.CV↗

arXiv2024

Harmonizing knowledge Transfer in Neural Network with Unified Distillation

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories emerge within KD methods: feature-based, focusing on intermediate layers' features, and logits-based, targeting the final layer's logits. This paper introduces a novel perspective by leveraging diverse knowledge sources within a unified KD framework. Specifically, we aggregate features from intermediate layers into a comprehensive representation, effectively gathering semantic information from different stages and scales. Subsequently, we predict the distribution parameters from this representation. These steps transform knowledge from the intermediate layers into corresponding distributive forms, thereby allowing for knowledge distillation through a unified distribution constraint at different stages of the network, ensuring the comprehensiveness and coherence of knowledge transfer. Numerous experiments were conducted to validate the effectiveness of the proposed method.

cs.CV↗

arXiv2024

Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation

Knowledge distillation has become widely recognized for its ability to transfer knowledge from a large teacher network to a compact and more streamlined student network. Traditional knowledge distillation methods primarily follow a teacher-oriented paradigm that imposes the task of learning the teacher's complex knowledge onto the student network. However, significant disparities in model capacity and architectural design hinder the student's comprehension of the complex knowledge imparted by the teacher, resulting in sub-optimal performance. This paper introduces a novel perspective emphasizing student-oriented and refining the teacher's knowledge to better align with the student's needs, thereby improving knowledge transfer effectiveness. Specifically, we present the Student-Oriented Knowledge Distillation (SoKD), which incorporates a learnable feature augmentation strategy during training to refine the teacher's knowledge of the student dynamically. Furthermore, we deploy the Distinctive Area Detection Module (DAM) to identify areas of mutual interest between the teacher and student, concentrating knowledge transfer within these critical areas to avoid transferring irrelevant information. This customized module ensures a more focused and effective knowledge distillation process. Our approach, functioning as a plug-in, could be integrated with various knowledge distillation methods. Extensive experimental results demonstrate the efficacy and generalizability of our method.

cs.CV↗

arXiv2024

Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstruction

Magnetic resonance imaging (MRI) tasks often involve multiple contrasts. Recently, numerous deep learning-based multi-contrast MRI super-resolution (SR) and reconstruction methods have been proposed to explore the complementary information from the multi-contrast images. However, these methods either construct parameter-sharing networks or manually design fusion rules, failing to accurately model the correlations between multi-contrast images and lacking certain interpretations. In this paper, we propose a multi-contrast convolutional dictionary (MC-CDic) model under the guidance of the optimization algorithm with a well-designed data fidelity term. Specifically, we bulid an observation model for the multi-contrast MR images to explicitly model the multi-contrast images as common features and unique features. In this way, only the useful information in the reference image can be transferred to the target image, while the inconsistent information will be ignored. We employ the proximal gradient algorithm to optimize the model and unroll the iterative steps into a deep CDic model. Especially, the proximal operators are replaced by learnable ResNet. In addition, multi-scale dictionaries are introduced to further improve the model performance. We test our MC-CDic model on multi-contrast MRI SR and reconstruction tasks. Experimental results demonstrate the superior performance of the proposed MC-CDic model against existing SOTA methods. Code is available at https://github.com/lpcccc-cv/MC-CDic.

eess.IV↗

arXiv2023

Three-Stage Cascade Framework for Blurry Video Frame Interpolation

Blurry video frame interpolation (BVFI) aims to generate high-frame-rate clear videos from low-frame-rate blurry videos, is a challenging but important topic in the computer vision community. Blurry videos not only provide spatial and temporal information like clear videos, but also contain additional motion information hidden in each blurry frame. However, existing BVFI methods usually fail to fully leverage all valuable information, which ultimately hinders their performance. In this paper, we propose a simple end-to-end three-stage framework to fully explore useful information from blurry videos. The frame interpolation stage designs a temporal deformable network to directly sample useful information from blurry inputs and synthesize an intermediate frame at an arbitrary time interval. The temporal feature fusion stage explores the long-term temporal information for each target frame through a bi-directional recurrent deformable alignment network. And the deblurring stage applies a transformer-empowered Taylor approximation network to recursively recover the high-frequency details. The proposed three-stage framework has clear task assignment for each module and offers good expandability, the effectiveness of which are demonstrated by various experimental results. We evaluate our model on four benchmarks, including the Adobe240 dataset, GoPro dataset, YouTube240 dataset and Sony dataset. Quantitative and qualitative results indicate that our model outperforms existing SOTA methods. Besides, experiments on real-world blurry videos also indicate the good generalization ability of our model.

cs.CV↗

arXiv2023

CP$^3$: Channel Pruning Plug-in for Point-based Networks

Channel pruning can effectively reduce both computational cost and memory footprint of the original network while keeping a comparable accuracy performance. Though great success has been achieved in channel pruning for 2D image-based convolutional networks (CNNs), existing works seldom extend the channel pruning methods to 3D point-based neural networks (PNNs). Directly implementing the 2D CNN channel pruning methods to PNNs undermine the performance of PNNs because of the different representations of 2D images and 3D point clouds as well as the network architecture disparity. In this paper, we proposed CP$^3$, which is a Channel Pruning Plug-in for Point-based network. CP$^3$ is elaborately designed to leverage the characteristics of point clouds and PNNs in order to enable 2D channel pruning methods for PNNs. Specifically, it presents a coordinate-enhanced channel importance metric to reflect the correlation between dimensional information and individual channel features, and it recycles the discarded points in PNN's sampling process and reconsiders their potentially-exclusive information to enhance the robustness of channel pruning. Experiments on various PNN architectures show that CP$^3$ constantly improves state-of-the-art 2D CNN pruning approaches on different point cloud tasks. For instance, our compressed PointNeXt-S on ScanObjectNN achieves an accuracy of 88.52% with a pruning rate of 57.8%, outperforming the baseline pruning methods with an accuracy gain of 1.94%.

cs.CV↗

arXiv2022

Flow Guidance Deformable Compensation Network for Video Frame Interpolation

Motion-based video frame interpolation (VFI) methods have made remarkable progress with the development of deep convolutional networks over the past years. While their performance is often jeopardized by the inaccuracy of flow map estimation, especially in the case of large motion and occlusion. In this paper, we propose a flow guidance deformable compensation network (FGDCN) to overcome the drawbacks of existing motion-based methods. FGDCN decomposes the frame sampling process into two steps: a flow step and a deformation step. Specifically, the flow step utilizes a coarse-to-fine flow estimation network to directly estimate the intermediate flows and synthesizes an anchor frame simultaneously. To ensure the accuracy of the estimated flow, a distillation loss and a task-oriented loss are jointly employed in this step. Under the guidance of the flow priors learned in step one, the deformation step designs a pyramid deformable compensation network to compensate for the missing details of the flow step. In addition, a pyramid loss is proposed to supervise the model in both the image and frequency domain. Experimental results show that the proposed algorithm achieves excellent performance on various datasets with fewer parameters.

cs.CV↗

arXiv2022

Label-Guided Auxiliary Training Improves 3D Object Detector

Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3D), which serves as an auxiliary network to enhance the feature learning of existing 3D object detectors. Specifically, we propose two novel modules: a Label-Annotation-Inducer that maps annotations and point clouds in bounding boxes to task-specific representations and a Label-Knowledge-Mapper that assists the original features to obtain detection-critical representations. The proposed auxiliary network is discarded in inference and thus has no extra computational cost at test time. We conduct extensive experiments on both indoor and outdoor datasets to verify the effectiveness of our approach. For example, our proposed LG3D improves VoteNet by 2.5% and 3.1% mAP on the SUN RGB-D and ScanNetV2 datasets, respectively.

cs.CV↗

arXiv2022

Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation

Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning. However, the proposed methods are often accompanied by plenty of parameters, which greatly limits their application scenarios. Different from previous works that blindly increase the depth of the network, we explore the degradation mechanism of the noisy image and propose a lightweight Multiple Degradation and Reconstruction Network (MDRN) to progressively remove noise. Meanwhile, we propose two novel Heterogeneous Knowledge Distillation Strategies (HMDS) to enable MDRN to learn richer and more accurate features from heterogeneous models, which make it possible to reconstruct higher-quality denoised images under extreme conditions. Extensive experiments show that our MDRN achieves favorable performance against other SID models with fewer parameters. Meanwhile, plenty of ablation studies demonstrate that the introduced HMDS can improve the performance of tiny models or the model under high noise levels, which is extremely useful for related applications.

cs.CV↗

arXiv2022

Hybrid Atlas Building with Deep Registration Priors

Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fast estimates atlas from large-scale image datasets with much reduced computational cost. In contrast to previous approaches that iteratively perform registration tasks between an estimated atlas and individual images, we propose to use learned priors of registration from pre-trained neural networks. This newly developed hybrid framework features several advantages of (i) providing an efficient way of atlas building without losing the quality of results, and (ii) offering flexibility in utilizing a wide variety of deep learning based registration methods. We demonstrate the effectiveness of this proposed model on 3D brain magnetic resonance imaging (MRI) scans.

cs.CV↗

arXiv2021

Contrastive Learning for Local and Global Learning MRI Reconstruction

Magnetic Resonance Imaging (MRI) is an important medical imaging modality, while it requires a long acquisition time. To reduce the acquisition time, various methods have been proposed. However, these methods failed to reconstruct images with a clear structure for two main reasons. Firstly, similar patches widely exist in MR images, while most previous deep learning-based methods ignore this property and only adopt CNN to learn local information. Secondly, the existing methods only use clear images to constrain the upper bound of the solution space, while the lower bound is not constrained, so that a better parameter of the network cannot be obtained. To address these problems, we propose a Contrastive Learning for Local and Global Learning MRI Reconstruction Network (CLGNet). Specifically, according to the Fourier theory, each value in the Fourier domain is calculated from all the values in Spatial domain. Therefore, we propose a Spatial and Fourier Layer (SFL) to simultaneously learn the local and global information in Spatial and Fourier domains. Moreover, compared with self-attention and transformer, the SFL has a stronger learning ability and can achieve better performance in less time. Based on the SFL, we design a Spatial and Fourier Residual block as the main component of our model. Meanwhile, to constrain the lower bound and upper bound of the solution space, we introduce contrastive learning, which can pull the result closer to the clear image and push the result further away from the undersampled image. Extensive experimental results on different datasets and acceleration rates demonstrate that the proposed CLGNet achieves new state-of-the-art results.

eess.IV↗

arXiv2021

Structure-Preserving Deraining with Residue Channel Prior Guidance

Single image deraining is important for many high-level computer vision tasks since the rain streaks can severely degrade the visibility of images, thereby affecting the recognition and analysis of the image. Recently, many CNN-based methods have been proposed for rain removal. Although these methods can remove part of the rain streaks, it is difficult for them to adapt to real-world scenarios and restore high-quality rain-free images with clear and accurate structures. To solve this problem, we propose a Structure-Preserving Deraining Network (SPDNet) with RCP guidance. SPDNet directly generates high-quality rain-free images with clear and accurate structures under the guidance of RCP but does not rely on any rain-generating assumptions. Specifically, we found that the RCP of images contains more accurate structural information than rainy images. Therefore, we introduced it to our deraining network to protect structure information of the rain-free image. Meanwhile, a Wavelet-based Multi-Level Module (WMLM) is proposed as the backbone for learning the background information of rainy images and an Interactive Fusion Module (IFM) is designed to make full use of RCP information. In addition, an iterative guidance strategy is proposed to gradually improve the accuracy of RCP, refining the result in a progressive path. Extensive experimental results on both synthetic and real-world datasets demonstrate that the proposed model achieves new state-of-the-art results. Code: https://github.com/Joyies/SPDNet

cs.CV↗