Author name cluster

Bin Xia

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

AAAI Conference 2025 Conference Paper

GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution

Jintong Hu
Bin Xia
Bin Chen
Wenming Yang
Lei Zhang

Implicit neural representations (INRs) have revolutionized arbitrary-scale super-resolution (ASSR) by modeling images as continuous functions. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features. In this paper, we propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS). Unlike traditional methods that treat pixels as discrete points, GaussianSR represents each pixel as a continuous Gaussian field. The encoded features are simultaneously refined and upsampled by rendering the mutually stacked Gaussian fields. As a result, long-range dependencies are established to enhance representation ability. In addition, a classifier is developed to dynamically assign Gaussian kernels to all pixels to further improve flexibility. All components of GaussianSR (i.e. encoder, classifier, Gaussian kernels, and decoder) are jointly learned end-to-end. Experiments demonstrate that GaussianSR achieves superior ASSR performance with fewer parameters than existing methods while enjoying interpretable and content-aware feature aggregations.

PDF Details DOI

ICML Conference 2025 Conference Paper

GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning

Zhun Mou
Bin Xia
Zhengchao Huang
Wenming Yang
Jiaya Jia

Recent great advances in video generation models have demonstrated their potential to produce high-quality videos, bringing challenges to effective evaluation. Unlike human evaluation, existing automated evaluation metrics lack high-level semantic understanding and reasoning capabilities for video, thus making them infeasible and unexplainable. To fill this gap, we curate GRADEO-Instruct, a multi-dimensional T2V evaluation instruction tuning dataset, including 3. 3k videos from over 10 existing video generation models and multi-step reasoning assessments converted by 16k human annotations. We then introduce GRADEO, one of the first specifically designed video evaluation models, which grades AI-generated videos for explainable scores and assessments through multi-step reasoning. Experiments show that our method aligns better with human evaluations than existing methods. Furthermore, our benchmarking reveals that current video generation models struggle to produce content that aligns with human reasoning and complex real-world scenarios. The models, datasets, and codes will be released soon.

Details

NeurIPS Conference 2025 Conference Paper

Training-Free Efficient Video Generation via Dynamic Token Carving

Yuechen Zhang
Jinbo Xing
Bin Xia
Shaoteng Liu
Bohao PENG
Xin Tao
Pengfei Wan
Eric Lo

Despite the remarkable generation quality of video Diffusion Transformer (DiT) models, their practical deployment is severely hindered by extensive computational requirements. This inefficiency stems from two key challenges: the quadratic complexity of self-attention with respect to token length and the multi-step nature of diffusion models. To address these limitations, we present Jenga, a novel inference pipeline that combines dynamic attention carving with progressive resolution generation. Our approach leverages two key insights: (1) early denoising steps do not require high-resolution latents, and (2) later steps do not require dense attention. Jenga introduces a block-wise attention mechanism that dynamically selects relevant token interactions using 3D space-filling curves, alongside a progressive resolution strategy that gradually increases latent resolution during generation. Experimental results demonstrate that Jenga achieves substantial speedups across multiple state-of-the-art video diffusion models while maintaining comparable generation quality (8. 83$\times$ speedup with 0. 01\% performance drop on VBench). As a plug-and-play solution, Jenga enables practical, high-quality video generation on modern hardware by reducing inference time from minutes to seconds---without requiring model retraining.

PDF Details

NeurIPS Conference 2025 Conference Paper

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Ruihang Chu
Yefei He
Zhekai Chen
Shiwei Zhang
Xiaogang Xu
Bin Xia
Dingdong WANG
Hongwei Yi

We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs insufficient for practical use. We narrow this gap by achieving precise and high-quality motion control. Our core idea is to directly make the original condition features motion-aware for guiding video synthesis. To this end, we first represent object motions with dense point trajectories, allowing fine-grained control over the scene. We then project these trajectories into latent space and propagate the first frame's features along each trajectory, producing an aligned spatiotemporal feature map that tells how each scene element should move. This feature map serves as the updated latent condition, which is naturally integrated into the off-the-shelf image-to-video model, e. g. , Wan-I2V-14B, as motion guidance without any architecture change. It removes the need for auxiliary motion encoders and makes fine-tuning base models easily scalable. Through scaled training, Wan-Move generates 5-second, 480p videos whose motion controllability rivals Kling 1. 5 Pro's commercial Motion Brush, as indicated by user studies. To support comprehensive evaluation, we further design MoveBench, a rigorously curated benchmark featuring diverse content categories and hybrid-verified annotations. It is distinguished by larger data volume, longer video durations, and high-quality motion annotations. Extensive experiments on MoveBench and the public dataset consistently show Wan-Move's superior motion quality. Code, models, and benchmark data are made available.

PDF Details

ICLR Conference 2023 Conference Paper

Basic Binary Convolution Unit for Binarized Image Restoration Network

Bin Xia
Yulun Zhang 0001
Yitong Wang
Yapeng Tian
Wenming Yang
Radu Timofte
Luc Van Gool

Lighter and faster image restoration (IR) models are crucial for the deployment on resource-limited devices. Binary neural network (BNN), one of the most promising model compression methods, can dramatically reduce the computations and parameters of full-precision convolutional neural networks (CNN). However, there are different properties between BNN and full-precision CNN, and we can hardly use the experience of designing CNN to develop BNN. In this study, we reconsider components in binary convolution, such as residual connection, BatchNorm, activation function, and structure, for IR tasks. We conduct systematic analyses to explain each component's role in binary convolution and discuss the pitfalls. Specifically, we find that residual connection can reduce the information loss caused by binarization; BatchNorm can solve the value range gap between residual connection and binary convolution; The position of the activation function dramatically affects the performance of BNN. Based on our findings and analyses, we design a simple yet efficient basic binary convolution unit (BBCU). Furthermore, we divide IR networks into four parts and specially design variants of BBCU for each part to explore the benefit of binarizing these parts. We conduct experiments on different IR tasks, and our BBCU significantly outperforms other BNNs and lightweight models, which shows that BBCU can serve as a basic unit for binarized IR networks. All codes and models will be released.

Details

TIST Journal 2023 Journal Article

Cost-sensitive Tensor-based Dual-stage Attention LSTM with Feature Selection for Data Center Server Power Forecasting

Ziyu Shen
Binghui Liu
Qing Zhou
Zheng Liu
Bin Xia
Yun Li

Power forecasting has a guiding effect on power-aware scheduling strategies to reduce unnecessary power consumption in data centers. Many metrics related to power consumption can be collected in physical servers, such as the status of CPU, memory, and other components. However, most existing methods empirically exploit a small number of metrics to forecast power consumption. To this end, this article uses feature selection based on causality to explore the metrics that strongly influence the power consumption of different tasks. Moreover, we propose a tensor-based dual-stage attention LSTM to forecast the non-linear and non-periodic power consumption. In the proposed model, a multi-way delay embedding transform is utilized to convert the time series into tensors along the temporal direction. The LSTM combines with the tensor technique and the attention mechanism to capture the temporal pattern effectively. In addition, we adopt the cost-sensitive loss function to optimize the specific power forecasting problem in data centers. The experimental results demonstrate that our method can achieve up to 1.4% to 4.3% forecasting accuracy improvement compared with the state-of-the-art models.

Details DOI

NeurIPS Conference 2023 Conference Paper

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

Zheng Chen
Yulun Zhang
Ding Liu
Bin Xia
Jinjin Gu
Linghe Kong
Xin Yuan

Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consumes massive computational resources. Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process. The deblurring process is implemented by a regression-based method to obtain better distortion accuracy. Meanwhile, the highly compact latent space ensures the efficiency of the DM. Furthermore, we design the hierarchical integration module to fuse the prior into the regression-based model from multiple scales, enabling better generalization in complex blurry scenarios. Comprehensive experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods. Code and trained models are available at https: //github. com/zhengchen1999/HI-Diff.

PDF Details

ICLR Conference 2023 Conference Paper

Knowledge Distillation based Degradation Estimation for Blind Super-Resolution

Bin Xia
Yulun Zhang 0001
Yitong Wang
Yapeng Tian
Wenming Yang
Radu Timofte
Luc Van Gool

Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from its corresponding low-resolution (LR) input image with unknown degradations. Most of the existing works design an explicit degradation estimator for each degradation to guide SR. However, it is infeasible to provide concrete labels of multiple degradation combinations (\eg, blur, noise, jpeg compression) to supervise the degradation estimator training. In addition, these special designs for certain degradation, such as blur, impedes the models from being generalized to handle different degradations. To this end, it is necessary to design an implicit degradation estimator that can extract discriminative degradation representation for all degradations without relying on the supervision of degradation ground-truth. In this paper, we propose a Knowledge Distillation based Blind-SR network (KDSR). It consists of a knowledge distillation based implicit degradation estimator network (KD-IDE) and an efficient SR network. To learn the KDSR model, we first train a teacher network: KD-IDE$_{T}$. It takes paired HR and LR patches as inputs and is optimized with the SR network jointly. Then, we further train a student network KD-IDE$_{S}$, which only takes LR images as input and learns to extract the same implicit degradation representation (IDR) as KD-IDE$_{T}$. In addition, to fully use extracted IDR, we design a simple, strong, and efficient IDR based dynamic convolution residual block (IDR-DCRB) to build an SR network. We conduct extensive experiments under classic and real-world degradation settings. The results show that KDSR achieves SOTA performance and can generalize to various degradation processes. The source codes and pre-trained models will be released.

Details

JBHI Journal 2022 Journal Article

Automatic Dental Plaque Segmentation Based on Local-to-Global Features Fused Self-Attention Network

Shuai Li
Yuting Guo
Zhennan Pang
Wenfeng Song
Aimin Hao
Bin Xia
Hong Qin

The accurate detection of dental plaque at an early stage will definitely prevent periodontal diseases and dental caries. However, it remains difficult for the current dental examination to accurately recognize dental plaque without using medical dyeing reagent due to the low contrast between dental plaque and healthy teeth. To combat this problem, this paper proposes a novel network enhanced by a self-attention module for intelligent dental plaque segmentation. The key motivation is to directly utilize oral endoscope images (bypassing the need for dyeing reagent) and get accurate pixel-level dental plaque segmentation results. The algorithm needs to conduct self-attention at the super-pixel level and fuse the super-pixels’ local-to-global features. Our newly-designed network architecture will afford the simultaneous fusion of multiple-scale complementary information guided by the powerful deep learning paradigm. The critical fused information includes the statistical distribution of the plaques color, the heat kernel signature (HKS) based local-to-global structure relationship, and the circle-LBP based local texture pattern in the nearby regions centering around the plaque area. To further refine the fuzed multiple-scale features, we devise an attention module based on CNN, which could focalize the regions of interest in plaque more easily, especially for many challenging cases. Extensive experiments and comprehensive evaluations confirm that, for a small-scale training dataset, our method could outperform the state-of-the-art methods. Meanwhile, the user studies verify the claim that our method is more accurate than conventional dental practice conducted by experienced dentists.

Details DOI

AAAI Conference 2022 Conference Paper

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-Based Super-resolution

Bin Xia
Yapeng Tian
Yucheng Hang
Wenming Yang
Qingmin Liao
Jie Zhou

Reference-based super-resolution (RefSR) has made significant progress in producing realistic textures using an external reference (Ref) image. However, existing RefSR methods obtain high-quality correspondence matchings consuming quadratic computation resources with respect to the input size, limiting its application. Moreover, these approaches usually suffer from scale misalignments between the lowresolution (LR) image and Ref image. In this paper, we propose an Accelerated Multi-Scale Aggregation network (AMSA) for Reference-based Super-Resolution, including Coarse-to-Fine Embedded PatchMatch (CFE-PatchMatch) and Multi-Scale Dynamic Aggregation (MSDA) module. To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size. To further reduce computational cost and speed up convergence, we apply the coarseto-fine strategy on Embedded PatchMacth constituting CFE- PatchMatch. To fully leverage reference information across multiple scales and enhance robustness to scale misalignment, we develop the MSDA module consisting of Dynamic Aggregation and Multi-Scale Aggregation. The Dynamic Aggregation corrects minor scale misalignment by dynamically aggregating features, and the Multi-Scale Aggregation brings robustness to large scale misalignment by fusing multi-scale information. Experimental results show that the proposed AMSA achieves superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.

PDF Details

AAAI Conference 2022 Conference Paper

Efficient Non-local Contrastive Attention for Image Super-resolution

Bin Xia
Yucheng Hang
Yapeng Tian
Wenming Yang
Qingmin Liao
Jie Zhou

Non-Local Attention (NLA) brings significant improvement for Single Image Super-Resolution (SISR) by leveraging intrinsic feature correlation in natural images. However, NLA gives noisy information large weights and consumes quadratic computation resources with respect to the input size, limiting its performance and application. In this paper, we propose a novel Efficient Non-Local Contrastive Attention (ENLCA) to perform long-range visual modeling and leverage more relevant non-local features. Specifically, ENLCA consists of two parts, Efficient Non-Local Attention (ENLA) and Sparse Aggregation. ENLA adopts the kernel method to approximate exponential function and obtains linear computation complexity. For Sparse Aggregation, we multiply inputs by an amplification factor to focus on informative features, yet the variance of approximation increases exponentially. Therefore, contrastive learning is applied to further separate relevant and irrelevant features. To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone. Extensive experimental results show that ENLCN reaches superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.

PDF Details

IJCAI Conference 2021 Conference Paper

Micro-Expression Recognition Enhanced by Macro-Expression from Spatial-Temporal Domain

Bin Xia
Shangfei Wang

Facial micro-expression recognition has attracted much attention due to its objectiveness to reveal the true emotion of a person. However, the limited micro-expression datasets have posed a great challenge to train a high performance micro-expression classifier. Since micro-expression and macro-expression share some similarities in both spatial and temporal facial behavior patterns, we propose a macro-to-micro transformation framework for micro-expression recognition. Specifically, we first pretrain two-stream baseline model from micro-expression data and macro-expression data respectively, named MiNet and MaNet. Then, we introduce two auxiliary tasks to align the spatial and temporal features learned from micro-expression data and macro-expression data. In spatial domain, we introduce a domain discriminator to align the features of MiNet and MaNet. In temporal domain, we introduce relation classifier to predict the correct relation for temporal features from MaNet and MiNet. Finally, we propose contrastive loss to encourage the MiNet to give closely aligned features to all entries from the same class in each instance. Experiments on three benchmark databases demonstrate the superiority of the proposed method.

PDF Details DOI

JBHI Journal 2020 Journal Article

Simultaneous Diagnosis of Severity and Features of Diabetic Retinopathy in Fundus Photography Using Deep Learning

Juan Wang
Yujing Bai
Bin Xia

Deep learning methods for diabetic retinopathy (DR) diagnosis are usually criticized as being lack of interpretability in the diagnostic result, thus limiting their application in clinic. Simultaneous prediction of DR related features during the DR severity diagnosis is able to resolve this issue by providing supporting evidence (i. e. DR related features) for the diagnostic result (i. e. DR severity). In this study, we propose a hierarchical multi-task deep learning framework for simultaneous diagnosis of DR severity and DR related features in fundus images. A hierarchical structure is introduced to incorporate the casual relationship between DR related features and DR severity levels. In the experiments, the proposed approach was evaluated on two independent testing sets using quadratic weighted Cohen's kappa coefficient, receiver operating characteristic analysis, and precision-recall analysis. A grader study was also conducted to compare the performance of the proposed approach with those of general ophthalmologists with different levels of experience. The results demonstrate that the proposed approach could improve the performance for both DR severity diagnosis and DR related feature detection when comparing with the traditional deep learning-based methods. It achieves performance close to general ophthalmologists with five years of experience when diagnosing DR severity levels, and general ophthalmologists with ten years of experience for referable DR detection.

Details DOI