Qingmin Liao

Yidan Zhang, Ting Zhang, Dong Chen et al. · microsoft-research, pku

While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image retrieval as a variant of generative modeling and employing a sequence-to-sequence model. This approach is harmoniously aligned with the current trend towards unification in research, presenting a cohesive framework that allows for end-to-end differentiable searching. This, in turn, facilitates superior performance via direct optimization techniques. The development of our model, dubbed IRGen, addresses the critical technical challenge of converting an image into a concise sequence of semantic units, which is pivotal for enabling efficient and effective search. Extensive experiments demonstrate that our model achieves state-of-the-art performance on three widely-used image retrieval benchmarks as well as two million-scale datasets, yielding significant improvement compared to prior competitive retrieval methods. In addition, the notable surge in precision scores facilitated by generative modeling presents the potential to bypass the reranking phase, which is traditionally indispensable in practical retrieval workflows.

Hai Wang, Xiaoyu Xiang, Yapeng Tian et al.

The target of space-time video super-resolution (STVSR) is to increase the spatial-temporal resolution of low-resolution (LR) and low frame rate (LFR) videos. Recent approaches based on deep learning have made significant improvements, but most of them only use two adjacent frames, that is, short-term features, to synthesize the missing frame embedding, which cannot fully explore the information flow of consecutive input LR frames. In addition, existing STVSR models hardly exploit the temporal contexts explicitly to assist high-resolution (HR) frame reconstruction. To address these issues, in this paper, we propose a deformable attention network called STDAN for STVSR. First, we devise a long-short term feature interpolation (LSTFI) module, which is capable of excavating abundant content from more neighboring input frames for the interpolation process through a bidirectional RNN structure. Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction. Experimental results on several datasets demonstrate that our approach outperforms state-of-the-art STVSR methods. The code is available at https://github.com/littlewhitesea/STDAN.

Nian Li, Chen Gao, Mingyu Li et al.

The advent of artificial intelligence has led to a growing emphasis on data-driven modeling in macroeconomics, with agent-based modeling (ABM) emerging as a prominent bottom-up simulation paradigm. In ABM, agents (e.g., households, firms) interact within a macroeconomic environment, collectively generating market dynamics. Existing agent modeling typically employs predetermined rules or learning-based neural networks for decision-making. However, customizing each agent presents significant challenges, complicating the modeling of agent heterogeneity. Additionally, the influence of multi-period market dynamics and multifaceted macroeconomic factors are often overlooked in decision-making processes. In this work, we introduce EconAgent, a large language model-empowered agent with human-like characteristics for macroeconomic simulation. We first construct a simulation environment that incorporates various market dynamics driven by agents' decisions regarding work and consumption. Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms. Furthermore, we model the impact of macroeconomic trends using a memory module, which allows agents to reflect on past individual experiences and market dynamics. Simulation experiments show that EconAgent can make realistic decisions, leading to more reasonable macroeconomic phenomena compared to existing rule-based or learning-based agents. Our codes are released at https://github.com/tsinghua-fib-lab/ACL24-EconAgent.

Bin Xia, Yapeng Tian, Yulun Zhang et al. · eth-zurich

The most of CNN based super-resolution (SR) methods assume that the degradation is known (\eg, bicubic). These methods will suffer a severe performance drop when the degradation is different from their assumption. Therefore, some approaches attempt to train SR networks with the complex combination of multiple degradations to cover the real degradation space. To adapt to multiple unknown degradations, introducing an explicit degradation estimator can actually facilitate SR performance. However, previous explicit degradation estimation methods usually predict Gaussian blur with the supervision of groundtruth blur kernels, and estimation errors may lead to SR failure. Thus, it is necessary to design a method that can extract implicit discriminative degradation representation. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of groundtruth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDA$_{T}$ is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired low-resolution (LR) and corresponding high-resolution (HR) images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images.

Qinpeng Cui, Xinyi Zhang, Qiqi Bao et al.

Sampling from Diffusion Models can alternatively be seen as solving differential equations, where there is a challenge in balancing speed and image visual quality. ODE-based samplers offer rapid sampling time but reach a performance limit, whereas SDE-based samplers achieve superior quality, albeit with longer iterations. In this work, we formulate the sampling process as an Extended Reverse-Time SDE (ER SDE), unifying prior explorations into ODEs and SDEs. Theoretically, leveraging the semi-linear structure of ER SDE solutions, we offer exact solutions and approximate solutions for VP SDE and VE SDE, respectively. Based on the approximate solution space of the ER SDE, referred to as one-step prediction errors, we yield mathematical insights elucidating the rapid sampling capability of ODE solvers and the high-quality sampling ability of SDE solvers. Additionally, we unveil that VP SDE solvers stand on par with their VE SDE counterparts. Based on these findings, leveraging the dual advantages of ODE solvers and SDE solvers, we devise efficient high-quality samplers, namely ER-SDE-Solvers. Experimental results demonstrate that ER-SDE-Solvers achieve state-of-the-art performance across all stochastic samplers while maintaining efficiency of deterministic samplers. Specifically, on the ImageNet $128\times128$ dataset, ER-SDE-Solvers obtain 8.33 FID in only 20 function evaluations. Code is available at \href{https://github.com/QinpengCui/ER-SDE-Solver}{https://github.com/QinpengCui/ER-SDE-Solver}

Yuan Shi, Bin Xia, Rui Zhu et al.

Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented reality. While conventional CDSR methods typically rely on convolutional neural networks or transformers, diffusion models (DMs) have demonstrated notable effectiveness in high-level vision tasks. In this work, we present a novel CDSR paradigm that utilizes a diffusion model within the latent space to generate guidance for depth map super-resolution. The proposed method comprises a guidance generation network (GGN), a depth map super-resolution network (DSRN), and a guidance recovery network (GRN). The GGN is specifically designed to generate the guidance while managing its compactness. Additionally, we integrate a simple but effective feature fusion module and a transformer-style feature extraction module into the DSRN, enabling it to leverage guided priors in the extraction, fusion, and reconstruction of multi-model images. Taking into account both accuracy and efficiency, our proposed method has shown superior performance in extensive experiments when compared to state-of-the-art methods. Our codes will be made available at https://github.com/shiyuan7/DSR-Diff.

Junbo Zhao, Xuefei Ning, Enshu Liu et al. · tsinghua

Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even damages the prediction ability and different search spaces have different preferences for low-fidelity information types. To solve the problem and better fuse beneficial information provided by different types of low-fidelity information, we propose a novel dynamic ensemble predictor framework that comprises two steps. In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts. In the second step, we learn a gating network to dynamically output a set of weighting coefficients conditioned on each input neural architecture, which will be used to combine the predictions of different low-fidelity experts in a weighted sum. The overall predictor is optimized on a small set of actual architecture-performance data to fuse the knowledge from different low-fidelity experts to make the final prediction. We conduct extensive experiments across five search spaces with different architecture encoders under various experimental settings. Our method can easily be incorporated into existing predictor-based NAS frameworks to discover better architectures.

Qinpeng Cui, Yixuan Liu, Xinyi Zhang et al.

Diffusion-based image super-resolution (SR) models have attracted substantial interest due to their powerful image restoration capabilities. However, prevailing diffusion models often struggle to strike an optimal balance between efficiency and performance. Typically, they either neglect to exploit the potential of existing extensive pretrained models, limiting their generative capacity, or they necessitate a dozens of forward passes starting from random noises, compromising inference efficiency. In this paper, we present DoSSR, a Domain Shift diffusion-based SR model that capitalizes on the generative powers of pretrained diffusion models while significantly enhancing efficiency by initiating the diffusion process with low-resolution (LR) images. At the core of our approach is a domain shift equation that integrates seamlessly with existing diffusion models. This integration not only improves the use of diffusion prior but also boosts inference efficiency. Moreover, we advance our method by transitioning the discrete shift process to a continuous formulation, termed as DoS-SDEs. This advancement leads to the fast and customized solvers that further enhance sampling efficiency. Empirical results demonstrate that our proposed method achieves state-of-the-art performance on synthetic and real-world datasets, while notably requiring only 5 sampling steps. Compared to previous diffusion prior based methods, our approach achieves a remarkable speedup of 5-7 times, demonstrating its superior efficiency. Code: https://github.com/QinpengCui/DoSSR.

Yucheng Hang, Bin Xia, Wenming Yang et al.

Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the training, and at most introduce the corresponding composite image as a single negative sample for an auxiliary constraint, which leads to limited distortion knowledge, and further causes a too large solution space, making the generated harmonized image distorted. Besides, none of them jointly constrain from the foreground self-style and foreground-background style consistency, which exacerbates this problem. Moreover, recent region-aware adaptive instance normalization achieves great success but only considers the global background feature distribution, making the aligned foreground feature distribution biased. To address these issues, we propose a self-consistent style contrastive learning scheme (SCS-Co). By dynamically generating multiple negative samples, our SCS-Co can learn more distortion knowledge and well regularize the generated harmonized image in the style representation space from two aspects of the foreground self-style and foreground-background style consistency, leading to a more photorealistic visual result. In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity. Experiments demonstrate the superiority of our method over other state-of-the-art methods in both quantitative comparison and visual analysis.

Yating Liu, Yaowei Li, Zimo Liu et al.

Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query. The primary challenge lies in bridging the substantial gap between vision and language modalities, especially when dealing with limited large-scale datasets. In this paper, we introduce a CLIP-based Synergistic Knowledge Transfer (CSKT) approach for TPR. Specifically, to explore the CLIP's knowledge on input side, we first propose a Bidirectional Prompts Transferring (BPT) module constructed by text-to-image and image-to-text bidirectional prompts and coupling projections. Secondly, Dual Adapters Transferring (DAT) is designed to transfer knowledge on output side of Multi-Head Attention (MHA) in vision and language. This synergistic two-way collaborative mechanism promotes the early-stage feature fusion and efficiently exploits the existing knowledge of CLIP. CSKT outperforms the state-of-the-art approaches across three benchmark datasets when the training parameters merely account for 7.4% of the entire model, demonstrating its remarkable efficiency, effectiveness and generalization.

Ruikun Li, Huandong Wang, Jingtao Ding et al.

Data-driven dynamics prediction often fails under environmental shifts, while traditional fine-tuning remains computationally prohibitive for hardware-constrained or data-scarce applications. We propose DynaDiff, a generative meta-learning framework that transitions the paradigm from gradient-based tuning or modulation to direct weight-space generation. Specifically, we first abstract expert weights as novel weight graphs, utilizing multi-head attention to explicitly capture topological coupling within weights. Subsequently, we design a functional loss to ensure that the generated models achieve consistency with expert models in physical behavior. Finally, we develop a dynamics-informed prompter that extracts cross-domain physical and spectral features from observation sequences to condition the diffusion model. Experiments demonstrate that DynaDiff boosts average prediction accuracy by 10.78% over competitive baselines. Furthermore, by pre-constructing a model zoo of expert predictors, we amortize the fine-tuning overhead into a one-time offline cost, significantly boosting deployment efficiency in new environments.

Xinyi Zhang, Qiqi Bao, Qinpeng Cui et al.

Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work, we leverage recent advances in state space models and utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting local dependencies between joints. To address these issues, we propose a new attention-free hybrid spatiotemporal architecture named Hybrid Mamba-GCN (Pose Magic). This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and GCN, Pose Magic demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic achieves new SOTA results ($\downarrow 0.9 mm$) while saving $74.1\%$ FLOPs. In addition, Pose Magic exhibits optimal motion consistency and the ability to generalize to unseen sequence lengths.

Yiran Shi, Dongqi Guo, Tianchen Zhao et al. · tsinghua

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for resource-constrained edge platforms in real-world deployments. However, since different stages of VLA (observation, action generation and execution) must proceed sequentially, and wait for the completion of the preceding stage, the system suffers from frequent halting and high latency. To address this, We conduct a systematic analysis to identify the challenges for fast and fluent generation, and propose enabling VLAs with the ability to asynchronously parallelize across VLA stages in a "streaming" manner. First, we eliminate the reliance on action chunking and adopt action flow matching, which learns the trajectory of action flows rather than denoising chunk-wise actions. It overlaps the latency of action generation and execution. Second, we design an action saliency-aware adaptive observation mechanism, thereby overlapping the latency of execution and observation. Without sacrificing performance, StreamingVLA achieves substantial speedup and improves the fluency of execution. It achieves a 2.4 $\times$ latency speedup and reduces execution halting by 6.5 $\times$.

Jiawei Xu, Zongqing Lu, Qingmin Liao

Lack of texture often causes ambiguity in matching, and handling this issue is an important challenge in optical flow estimation. Some methods insert stacked transformer modules that allow the network to use global information of cost volume for estimation. But the global information aggregation often incurs serious memory and time costs during training and inference, which hinders model deployment. We draw inspiration from the traditional local region constraint and design the local similarity aggregation (LSA) and the shifted local similarity aggregation (SLSA). The aggregation for cost volume is implemented with lightweight modules that act on the feature maps. Experiments on the final pass of Sintel show the lower cost required for our approach while maintaining competitive performance.

Siqi Yang, Zilve Gao, Haibo Qiu et al.

Multimodal Large Language Models (MLLMs) demonstrate significant potential but remain brittle in complex, long-chain visual reasoning tasks. A critical failure mode is "visual forgetting", where models progressively lose visual grounding as reasoning extends, a phenomenon aptly described as "think longer, see less". We posit this failure stems from current training paradigms prematurely entangling two distinct cognitive skills: (1) abstract logical reasoning "how-to-think") and (2) strategic visual perception ("when-to-look"). This creates a foundational cold-start deficiency -- weakening abstract reasoning -- and a strategic perception deficit, as models lack a policy for when to perceive. In this paper, we propose a novel curriculum-based framework to disentangle these skills. First, we introduce a disentangled Supervised Fine-Tuning (SFT) curriculum that builds a robust abstract reasoning backbone on text-only data before anchoring it to vision with a novel Perception-Grounded Chain-of-Thought (PG-CoT) paradigm. Second, we resolve the strategic perception deficit by formulating timing as a reinforcement learning problem. We design a Pivotal Perception Reward that teaches the model when to look by coupling perceptual actions to linguistic markers of cognitive uncertainty (e.g., "wait", "verify"), thereby learning an autonomous grounding policy. Our contributions include the formalization of these two deficiencies and the development of a principled, two-stage framework to address them, transforming the model from a heuristic-driven observer to a strategic, grounded reasoner. \textbf{Code}: \url{https://github.com/gaozilve-max/learning-when-to-look}.

Yu Li, Lehui Li, Qingmin Liao et al.

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for facilitating scientific quest. One key application in AI research is to automate experiment design through agentic dataset and baseline retrieval. However, prior efforts suffer from limited data coverage, as recommendation datasets primarily harvest candidates from public portals and omit many datasets actually used in published papers, and from an overreliance on content similarity that biases model toward superficial similarity and overlooks experimental suitability. Harnessing collective perception embedded in the baseline and dataset citation network, we present a comprehensive framework for baseline and dataset recommendation. First, we design an automated data-collection pipeline that links roughly one hundred thousand accepted papers to the baselines and datasets they actually used. Second, we propose a collective perception enhanced retriever. To represent the position of each dataset or baseline within the scholarly network, it concatenates self-descriptions with aggregated citation contexts. To achieve efficient candidate recall, we finetune an embedding model on these representations. Finally, we develop a reasoning-augmented reranker that exact interaction chains to construct explicit reasoning chains and finetunes a large language model to produce interpretable justifications and refined rankings. The dataset we curated covers 85\% of the datasets and baselines used at top AI conferences over the past five years. On our dataset, the proposed method outperforms the strongest prior baseline with average gains of +5.85\% in Recall@20, +8.30\% in HitRate@5. Taken together, our results advance reliable, interpretable automation of experimental design.

Jingrui Ye, Zongkai Zhang, Yujiao Jiang et al.

Rendering dynamic 3D human from monocular videos is crucial for various applications such as virtual reality and digital entertainment. Most methods assume the people is in an unobstructed scene, while various objects may cause the occlusion of body parts in real-life scenarios. Previous method utilizing NeRF for surface rendering to recover the occluded areas, but it requiring more than one day to train and several seconds to render, failing to meet the requirements of real-time interactive applications. To address these issues, we propose OccGaussian based on 3D Gaussian Splatting, which can be trained within 6 minutes and produces high-quality human renderings up to 160 FPS with occluded input. OccGaussian initializes 3D Gaussian distributions in the canonical space, and we perform occlusion feature query at occluded regions, the aggregated pixel-align feature is extracted to compensate for the missing information. Then we use Gaussian Feature MLP to further process the feature along with the occlusion-aware loss functions to better perceive the occluded area. Extensive experiments both in simulated and real-world occlusions, demonstrate that our method achieves comparable or even superior performance compared to the state-of-the-art method. And we improving training and inference speeds by 250x and 800x, respectively. Our code will be available for research purposes.

Yating Liu, Yaowei Li, Xiangyuan Lan et al.

Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the progress of contrastive visual-language pre-trained model. Prior works leverage pre-trained CLIP to extract person visual and textual features and fully fine-tune the entire network, which have shown notable performance improvements compared to uni-modal pre-training models. However, full-tuning a large model is prone to overfitting and hinders the generalization ability. In this paper, we propose a novel Unified Parameter-Efficient Transfer Learning (PETL) method for Text-based Person Retrieval (UP-Person) to thoroughly transfer the multi-modal knowledge from CLIP. Specifically, UP-Person simultaneously integrates three lightweight PETL components including Prefix, LoRA and Adapter, where Prefix and LoRA are devised together to mine local information with task-specific information prompts, and Adapter is designed to adjust global feature representations. Additionally, two vanilla submodules are optimized to adapt to the unified architecture of TPR. For one thing, S-Prefix is proposed to boost attention of prefix and enhance the gradient propagation of prefix tokens, which improves the flexibility and performance of the vanilla prefix. For another thing, L-Adapter is designed in parallel with layer normalization to adjust the overall distribution, which can resolve conflicts caused by overlap and interaction among multiple submodules. Extensive experimental results demonstrate that our UP-Person achieves state-of-the-art results across various person retrieval datasets, including CUHK-PEDES, ICFG-PEDES and RSTPReid while merely fine-tuning 4.7\% parameters. Code is available at https://github.com/Liu-Yating/UP-Person.

Ruikun Li, Huandong Wang, Qingmin Liao et al.

Energy landscapes play a crucial role in shaping dynamics of many real-world complex systems. System evolution is often modeled as particles moving on a landscape under the combined effect of energy-driven drift and noise-induced diffusion, where the energy governs the long-term motion of the particles. Estimating the energy landscape of a system has been a longstanding interdisciplinary challenge, hindered by the high operational costs or the difficulty of obtaining supervisory signals. Therefore, the question of how to infer the energy landscape in the absence of true energy values is critical. In this paper, we propose a physics-informed self-supervised learning method to learn the energy landscape from the evolution trajectories of the system. It first maps the system state from the observation space to a discrete landscape space by an adaptive codebook, and then explicitly integrates energy into the graph neural Fokker-Planck equation, enabling the joint learning of energy estimation and evolution prediction. Experimental results across interdisciplinary systems demonstrate that our estimated energy has a correlation coefficient above 0.9 with the ground truth, and evolution prediction accuracy exceeds the baseline by an average of 17.65\%. The code is available at github.com/tsinghua-fib-lab/PESLA.

Qianyue Hao, Yiwen Song, Qingmin Liao et al.

Policy exploration is critical in reinforcement learning (RL), where existing approaches include greedy, Gaussian process, etc. However, these approaches utilize preset stochastic processes and are indiscriminately applied in all kinds of RL tasks without considering task-specific features that influence policy exploration. Moreover, during RL training, the evolution of such stochastic processes is rigid, which typically only incorporates a decay in the variance, failing to adjust flexibly according to the agent's real-time learning status. Inspired by the analyzing and reasoning capability of large language models (LLMs), we design LLM-Explorer to adaptively generate task-specific exploration strategies with LLMs, enhancing the policy exploration in RL. In our design, we sample the learning trajectory of the agent during the RL training in a given task and prompt the LLM to analyze the agent's current policy learning status and then generate a probability distribution for future policy exploration. Updating the probability distribution periodically, we derive a stochastic process specialized for the particular task and dynamically adjusted to adapt to the learning process. Our design is a plug-in module compatible with various widely applied RL algorithms, including the DQN series, DDPG, TD3, and any possible variants developed based on them. Through extensive experiments on the Atari and MuJoCo benchmarks, we demonstrate LLM-Explorer's capability to enhance RL policy exploration, achieving an average performance improvement up to 37.27%. Our code is open-source at https://github.com/tsinghua-fib-lab/LLM-Explorer for reproducibility.

Yiwen Song, Qianyue Hao, Qingmin Liao et al.

Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as algorithm selection, hyperparameter settings, and even random seed choices, all of which can significantly influence an agent's performance. Model ensemble helps overcome this challenge by combining multiple weak agents into a single, more powerful one, enhancing overall performance. However, existing ensemble methods, such as majority voting and Boltzmann addition, are designed as fixed strategies and lack a semantic understanding of specific tasks, limiting their adaptability and effectiveness. To address this, we propose LLM-Ens, a novel approach that enhances RL model ensemble with task-specific semantic understandings driven by large language models (LLMs). Given a task, we first design an LLM to categorize states in this task into distinct 'situations', incorporating high-level descriptions of the task conditions. Then, we statistically analyze the strengths and weaknesses of each individual agent to be used in the ensemble in each situation. During the inference time, LLM-Ens dynamically identifies the changing task situation and switches to the agent that performs best in the current situation, ensuring dynamic model selection in the evolving task condition. Our approach is designed to be compatible with agents trained with different random seeds, hyperparameter settings, and various RL algorithms. Extensive experiments on the Atari benchmark show that LLM-Ens significantly improves the RL model ensemble, surpassing well-known baselines by up to 20.9%. For reproducibility, our code is open-source at https://anonymous.4open.science/r/LLM4RLensemble-F7EE.

Xin Zhang, Yu Liu, Yuming Lin et al.

Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities. Traditionally, governments heavily depend on field survey methods to monitor the urban villages, which however are time-consuming, labor-intensive, and possibly delayed. Thanks to widely available and timely updated satellite images, recent studies develop computer vision techniques to detect urban villages efficiently. However, existing studies either focus on simple urban village image classification or fail to provide accurate boundary information. To accurately identify urban village boundaries from satellite images, we harness the power of the vision foundation model and adapt the Segment Anything Model (SAM) to urban village segmentation, named UV-SAM. Specifically, UV-SAM first leverages a small-sized semantic segmentation model to produce mixed prompts for urban villages, including mask, bounding box, and image representations, which are then fed into SAM for fine-grained boundary identification. Extensive experimental results on two datasets in China demonstrate that UV-SAM outperforms existing baselines, and identification results over multiple years show that both the number and area of urban villages are decreasing over time, providing deeper insights into the development trends of urban villages and sheds light on the vision foundation models for sustainable cities. The dataset and codes of this study are available at https://github.com/tsinghua-fib-lab/UV-SAM.

Yucheng Hang, Qingmin Liao, Wenming Yang et al.

Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of information. Besides, existing methods always use a multi-supervised method to aggregate different feature maps, which can not effectively aggregate hierarchical feature information. To address these issues, we propose an attention cube network (A-CubeNet) for image restoration for more powerful feature expression and feature correlation learning. Specifically, we design a novel attention mechanism from three dimensions, namely spatial dimension, channel-wise dimension and hierarchical dimension. The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations. Furthermore, the adaptive hierarchical attention module (AHAM) can capture the long-range hierarchical contextual information to flexibly aggregate different feature maps by weights depending on the global context. The ADAM and AHAM cooperate to form an "attention in attention" structure, which means AHAM's inputs are enhanced by ASAB and ACAB. Experiments demonstrate the superiority of our method over state-of-the-art image restoration methods in both quantitative comparison and visual analysis. Code is available at https://github.com/YCHang686/A-CubeNet.

Yujiao Jiang, Qingmin Liao, Xiaoyu Li et al.

Reconstructing photo-realistic drivable human avatars from multi-view image sequences has been a popular and challenging topic in the field of computer vision and graphics. While existing NeRF-based methods can achieve high-quality novel view rendering of human models, both training and inference processes are time-consuming. Recent approaches have utilized 3D Gaussians to represent the human body, enabling faster training and rendering. However, they undermine the importance of the mesh guidance and directly predict Gaussians in 3D space with coarse mesh guidance. This hinders the learning procedure of the Gaussians and tends to produce blurry textures. Therefore, we propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. We utilize the embedding of UV map to learn Gaussian textures in 2D space, leveraging the capabilities of powerful 2D networks to extract features. Additionally, through an independent Mesh network, we optimize pose-dependent geometric deformations, thereby guiding Gaussian rendering and significantly enhancing rendering quality. We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose. The code and data will be made available on the homepage https://alex-jyj.github.io/UV-Gaussians/ once the paper is accepted.

Yating Liu, Zimo Liu, Xiangyuan Lan et al.

Text-based person retrieval (TPR) has gained significant attention as a fine-grained and challenging task that closely aligns with practical applications. Tailoring CLIP to person domain is now a emerging research topic due to the abundant knowledge of vision-language pretraining, but challenges still remain during fine-tuning: (i) Previous full-model fine-tuning in TPR is computationally expensive and prone to overfitting.(ii) Existing parameter-efficient transfer learning (PETL) for TPR lacks of fine-grained feature extraction. To address these issues, we propose Domain-Aware Mixture-of-Adapters (DM-Adapter), which unifies Mixture-of-Experts (MOE) and PETL to enhance fine-grained feature representations while maintaining efficiency. Specifically, Sparse Mixture-of-Adapters is designed in parallel to MLP layers in both vision and language branches, where different experts specialize in distinct aspects of person knowledge to handle features more finely. To promote the router to exploit domain information effectively and alleviate the routing imbalance, Domain-Aware Router is then developed by building a novel gating function and injecting learnable domain-aware prompts. Extensive experiments show that our DM-Adapter achieves state-of-the-art performance, outperforming previous methods by a significant margin.

Zhehan Kan, Ce Zhang, Zihan Liao et al.

Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems. Despite previous efforts to mitigate hallucinations, a persistent issue remains: visual defect from vision-language misalignment, creating a bottleneck in visual processing capacity. To address this challenge, we develop Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs (CATCH), based on the Information Bottleneck theory. CATCH introduces Complementary Visual Decoupling (CVD) for visual information separation, Non-Visual Screening (NVS) for hallucination detection, and Adaptive Token-level Contrastive Decoding (ATCD) for hallucination mitigation. CATCH addresses issues related to visual defects that cause diminished fine-grained feature perception and cumulative hallucinations in open-ended scenarios. It is applicable to various visual question-answering tasks without requiring any specific data or prior knowledge, and generalizes robustly to new tasks without additional training, opening new possibilities for advancing LVLM in various challenging applications.

Yanjun Liu, Wenming Yang, Qingmin Liao

Finger vein authentication, recognized for its high security and specificity, has become a focal point in biometric research. Traditional methods predominantly concentrate on vein feature extraction for discriminative modeling, with a limited exploration of generative approaches. Suffering from verification failure, existing methods often fail to obtain authentic vein patterns by segmentation. To fill this gap, we introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks. DiffVein is composed of two dedicated branches: one for segmentation and the other for denoising. For better feature interaction between these two branches, we introduce two specialized modules to improve their collective performance. The first, a mask condition module, incorporates the semantic information of vein patterns from the segmentation branch into the denoising process. Additionally, we also propose a Semantic Difference Transformer (SD-Former), which employs Fourier-space self-attention and cross-attention modules to extract category embedding before feeding it to the segmentation task. In this way, our framework allows for a dynamic interplay between diffusion and segmentation embeddings, thus vein segmentation and authentication tasks can inform and enhance each other in the joint training. To further optimize our model, we introduce a Fourier-space Structural Similarity (FourierSIM) loss function, which is tailored to improve the denoising network's learning efficacy. Extensive experiments on the USM and THU-MVFV3V datasets substantiates DiffVein's superior performance, setting new benchmarks in both vein segmentation and authentication tasks.

Lingting Zhu, Jingrui Ye, Runze Zhang et al.

Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials. In this work, we propose MuMA, a method for 3D PBR texturing through Multi-channel Multi-view generation and Agentic post-processing. Our approach features two key innovations: 1) We opt to model shaded and albedo appearance channels, where the shaded channels enables the integration intrinsic decomposition modules for material properties. 2) Leveraging multimodal large language models, we emulate artists' techniques for material assessment and selection. Experiments demonstrate that MuMA achieves superior results in visual quality and material fidelity compared to existing methods.

Zhehan Kan, Yanlin Liu, Kun Yin et al. · tencent-ai

DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings, they face limitations, including inconsistencies between reasoning and final answers, model instability and crashes during long-chain exploration, and low data learning efficiency. To address these challenges, we propose TACO, a novel reinforcement learning algorithm for visual reasoning. Building on Generalized Reinforcement Policy Optimization (GRPO), TACO introduces Think-Answer Consistency, which tightly couples reasoning with answer consistency to ensure answers are grounded in thoughtful reasoning. We also introduce the Rollback Resample Strategy, which adaptively removes problematic samples and reintroduces them to the sampler, enabling stable long-chain exploration and future learning opportunities. Additionally, TACO employs an adaptive learning schedule that focuses on moderate difficulty samples to optimize data efficiency. Furthermore, we propose the Test-Time-Resolution-Scaling scheme to address performance degradation due to varying resolutions during reasoning while balancing computational overhead. Extensive experiments on in-distribution and out-of-distribution benchmarks for REC and VQA tasks show that fine-tuning LVLMs leads to significant performance improvements.

Yifan Wang, Xiaochen Yang, Fanqi Pu et al.

Monocular 3D object detection has attracted great attention due to simplicity and low cost. Existing methods typically follow conventional 2D detection paradigms, first locating object centers and then predicting 3D attributes via neighboring features. However, these methods predominantly rely on progressive cross-scale feature aggregation and focus solely on local information, which may result in a lack of global awareness and the omission of small-scale objects. In addition, due to large variation in object scales across different scenes and depths, inaccurate receptive fields often lead to background noise and degraded feature representation. To address these issues, we introduces MonoASRH, a novel monocular 3D detection framework composed of Efficient Hybrid Feature Aggregation Module (EH-FAM) and Adaptive Scale-Aware 3D Regression Head (ASRH). Specifically, EH-FAM employs multi-head attention with a global receptive field to extract semantic features for small-scale objects and leverages lightweight convolutional modules to efficiently aggregate visual features across different scales. The ASRH encodes 2D bounding box dimensions and then fuses scale features with the semantic features aggregated by EH-FAM through a scale-semantic feature fusion module. The scale-semantic feature fusion module guides ASRH in learning dynamic receptive field offsets, incorporating scale priors into 3D position prediction for better scale-awareness. Extensive experiments on the KITTI and Waymo datasets demonstrate that MonoASRH achieves state-of-the-art performance.

Shengyuan Wang, Zhiheng Zheng, Yu Shang et al.

City-scale 3D generation is of great importance for the development of embodied intelligence and world models. Existing methods, however, face significant challenges regarding quality, fidelity, and scalability in 3D world generation. Thus, we propose RAISECity, a \textbf{R}eality-\textbf{A}ligned \textbf{I}ntelligent \textbf{S}ynthesis \textbf{E}ngine that creates detailed, \textbf{C}ity-scale 3D worlds. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyses validate the superior performance of RAISECity in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving over a 90% win-rate against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes RAISECity a promising foundation for applications in immersive media, embodied intelligence, and world models.

Jingrui Ye, Lingting Zhu, Runze Zhang et al.

The increasing demand for 3D assets across various industries necessitates efficient and automated methods for 3D content creation. Leveraging 3D Gaussian Splatting, recent large reconstruction models (LRMs) have demonstrated the ability to efficiently achieve high-quality 3D rendering by integrating multiview diffusion for generation and scalable transformers for reconstruction. However, existing models fail to produce the material properties of assets, which is crucial for realistic rendering in diverse lighting environments. In this paper, we introduce the Large Material Gaussian Model (MGM), a novel framework designed to generate high-quality 3D content with Physically Based Rendering (PBR) materials, ie, albedo, roughness, and metallic properties, rather than merely producing RGB textures with uncontrolled light baking. Specifically, we first fine-tune a new multiview material diffusion model conditioned on input depth and normal maps. Utilizing the generated multiview PBR images, we explore a Gaussian material representation that not only aligns with 2D Gaussian Splatting but also models each channel of the PBR materials. The reconstructed point clouds can then be rendered to acquire PBR attributes, enabling dynamic relighting by applying various ambient light maps. Extensive experiments demonstrate that the materials produced by our method not only exhibit greater visual appeal compared to baseline methods but also enhance material modeling, thereby enabling practical downstream rendering applications.

Jijia Liu, Feng Gao, Qingmin Liao et al.

Reinforcement learning (RL) for continuous control often requires large amounts of online interaction data. Value-based RL methods can mitigate this burden by offering relatively high sample efficiency. Some studies further enhance sample efficiency by incorporating offline demonstration data to "kick-start" training, achieving promising results in continuous control. However, they typically compute the Q-function independently for each action dimension, neglecting interdependencies and making it harder to identify optimal actions when learning from suboptimal data, such as non-expert demonstration and online-collected data during the training process. To address these issues, we propose Auto-Regressive Soft Q-learning (ARSQ), a value-based RL algorithm that models Q-values in a coarse-to-fine, auto-regressive manner. First, ARSQ decomposes the continuous action space into discrete spaces in a coarse-to-fine hierarchy, enhancing sample efficiency for fine-grained continuous control tasks. Next, it auto-regressively predicts dimensional action advantages within each decision step, enabling more effective decision-making in continuous control tasks. We evaluate ARSQ on two continuous control benchmarks, RLBench and D4RL, integrating demonstration data into online training. On D4RL, which includes non-expert demonstrations, ARSQ achieves an average $1.62\times$ performance improvement over SOTA value-based baseline. On RLBench, which incorporates expert demonstrations, ARSQ surpasses various baselines, demonstrating its effectiveness in learning from suboptimal online-collected data. Project page is at https://sites.google.com/view/ar-soft-q

Jijia Liu, Chao Yu, Jiaxuan Gao et al.

AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.

Bin Xia, Yapeng Tian, Yucheng Hang et al.

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 low-resolution (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 coarse-to-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.

Bin Xia, Yucheng Hang, Yapeng Tian et al.

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.

Jiacheng Chen, Bin-Bin Gao, Zongqing Lu et al.

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to incomplete feature comparisons. To address this issue, we present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes and thus construct complete sample pairs for learning semantic alignment with query features. The complementary features learning manner effectively enriches feature comparison and helps yield an unbiased segmentation model in the few-shot setting. It is implemented with a two-branch end-to-end network (i.e., a class-specific branch and a class-agnostic branch), which generates prototypes and then combines query features to perform comparisons. In addition, the proposed class-agnostic branch is simple yet effective. In practice, it can adaptively generate multiple class-agnostic prototypes for query images and learn feature alignment in a self-contrastive manner. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate the superiority of our method. At no expense of inference efficiency, our model achieves state-of-the-art results in both 1-shot and 5-shot settings for semantic segmentation.

Liyang Liu, Shilong Zhang, Zhanghui Kuang et al.

Network compression has been widely studied since it is able to reduce the memory and computation cost during inference. However, previous methods seldom deal with complicated structures like residual connections, group/depth-wise convolution and feature pyramid network, where channels of multiple layers are coupled and need to be pruned simultaneously. In this paper, we present a general channel pruning approach that can be applied to various complicated structures. Particularly, we propose a layer grouping algorithm to find coupled channels automatically. Then we derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Moreover, we find that inference speedup on GPUs is more correlated with the reduction of memory rather than FLOPs, and thus we employ the memory reduction of each channel to normalize the importance. Our method can be used to prune any structures including those with coupled channels. We conduct extensive experiments on various backbones, including the classic ResNet and ResNeXt, mobile-friendly MobileNetV2, and the NAS-based RegNet, both on image classification and object detection which is under-explored. Experimental results validate that our method can effectively prune sophisticated networks, boosting inference speed without sacrificing accuracy.

Jiacheng Chen, Bin-Bin Gao, Zongqing Lu et al.

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through matching each pixel to a learned foreground prototype. However, this framework suffers from biased classification due to incomplete construction of sample pairs with the foreground prototype only. To address this issue, in this paper, we introduce a complementary self-contrastive task into few-shot semantic segmentation. Our new model is able to associate the pixels in a region with the prototype of this region, no matter they are in the foreground or background. To this end, we generate self-contrastive background prototypes directly from the query image, with which we enable the construction of complete sample pairs and thus a complementary and auxiliary segmentation task to achieve the training of a better segmentation model. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate clearly the superiority of our proposal. At no expense of inference efficiency, our model achieves state-of-the results in both 1-shot and 5-shot settings for few-shot semantic segmentation.

Kai Lv, Zongqing Lu, Qingmin Liao

Matching keypoint pairs of different images is a basic task of computer vision. Most methods require customized extremum point schemes to obtain the coordinates of feature points with high confidence, which often need complex algorithmic design or a network with higher training difficulty and also ignore the possibility that flat regions can be used as candidate regions of matching points. In this paper, we design a region-based descriptor by combining the context features of a deep network. The new descriptor can give a robust representation of a point even in flat regions. By the new descriptor, we can obtain more high confidence matching points without extremum operation. The experimental results show that our proposed method achieves a performance comparable to state-of-the-art.

Yang Chen, Zongqing Lu, Xuechen Zhang et al.

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms. Especially, matching cost volume, one of the most important procedure, is treated as a normal intermediate feature for the following softargmin regression, lacking explicit constraints compared with those traditional algorithms. In this paper, inspired by previous canonical definition of cost volume, we propose the noise-sampling cross entropy loss function to regularize the cost volume produced by deep neural networks to be unimodal and coherent. Extensive experiments validate that the proposed noise-sampling cross entropy loss can not only help neural networks learn more informative cost volume, but also lead to better stereo matching performance compared with several representative algorithms.

Juncheng Zhang, Qingmin Liao, Shaojun Liu et al.

Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform convincing evaluation and comparison of algorithms in multi-focus image fusion. Moreover, it is difficult to train a deep neural network for multi-focus image fusion without a suitable dataset. In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images. The dataset is generated by light field images, and both the source images and the ground truth images are realistic. To serve as both a well-established benchmark for existing multi-focus image fusion algorithms and an appropriate training dataset for future development of deep-learning-based methods, the dataset contains a variety of scenes, including buildings, plants, humans, shopping malls, squares and so on. We also evaluate 10 typical multi-focus algorithms on this dataset for the purpose of illustration.

Jiarong Chen, Zongqing Lu, Jing-Hao Xue et al.

Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes ($\ge5$) have been applied to it recently. In this paper, we propose a novel extremely separated convolutional block (XSepConv), which fuses spatially separable convolutions into depthwise convolution to further reduce both the computational cost and parameter size of large kernels. Furthermore, an extra $2\times2$ depthwise convolution coupled with improved symmetric padding strategy is employed to compensate for the side effect brought by spatially separable convolutions. XSepConv is designed to be an efficient alternative to vanilla depthwise convolution with large kernel sizes. To verify this, we use XSepConv for the state-of-the-art architecture MobileNetV3-Small and carry out extensive experiments on four highly competitive benchmark datasets (CIFAR-10, CIFAR-100, SVHN and Tiny-ImageNet) to demonstrate that XSepConv can indeed strike a better trade-off between accuracy and efficiency.

Haoyu Ma, Qingmin Liao, Juncheng Zhang et al.

Capturing an all-in-focus image with a single camera is difficult since the depth of field of the camera is usually limited. An alternative method to obtain the all-in-focus image is to fuse several images focusing at different depths. However, existing multi-focus image fusion methods cannot obtain clear results for areas near the focused/defocused boundary (FDB). In this paper, a novel α-matte boundary defocus model is proposed to generate realistic training data with the defocus spread effect precisely modeled, especially for areas near the FDB. Based on this α-matte defocus model and the generated data, a cascaded boundary aware convolutional network termed MMF-Net is proposed and trained, aiming to achieve clearer fusion results around the FDB. More specifically, the MMF-Net consists of two cascaded sub-nets for initial fusion and boundary fusion, respectively; these two sub-nets are designed to first obtain a guidance map of FDB and then refine the fusion near the FDB. Experiments demonstrate that with the help of the new α-matte boundary defocus model, the proposed MMF-Net outperforms the state-of-the-art methods both qualitatively and quantitatively.

Wenming Yang, Xuechen Zhang, Yapeng Tian et al.

In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution. Compared with two representative network architectures with skip connections, ResNet and DenseNet, a linear compressing layer is designed in LCSCNet for skip connection, which connects former feature maps and distinguishes them from newly-explored feature maps. In this way, the proposed LCSCNet enjoys the merits of the distinguish feature treatment of DenseNet and the parameter-economic form of ResNet. Moreover, to better exploit hierarchical information from both low and high levels of various receptive fields in deep models, inspired by gate units in LSTM, we also propose an adaptive element-wise fusion strategy with multi-supervised training. Experimental results in comparison with state-of-the-art algorithms validate the effectiveness of LCSCNet.

Haoyu Ma, Juncheng Zhang, Shaojun Liu et al.

Since it is usually difficult to capture an all-in-focus image of a 3D scene directly, various multi-focus image fusion methods are employed to generate it from several images focusing at different depths. However, the performance of existing methods is barely satisfactory and often degrades for areas near the focused/defocused boundary (FDB). In this paper, a boundary aware method using deep neural network is proposed to overcome this problem. (1) Aiming to acquire improved fusion images, a 2-channel deep network is proposed to better extract the relative defocus information of the two source images. (2) After analyzing the different situations for patches far away from and near the FDB, we use two networks to handle them respectively. (3) To simulate the reality more precisely, a new approach of dataset generation is designed. Experiments demonstrate that the proposed method outperforms the state-of-the-art methods, both qualitatively and quantitatively.

Wenming Yang, Wei Wang, Xuechen Zhang et al.

Single image super-resolution(SISR) has witnessed great progress as convolutional neural network(CNN) gets deeper and wider. However, enormous parameters hinder its application to real world problems. In this letter, We propose a lightweight feature fusion network (LFFN) that can fully explore multi-scale contextual information and greatly reduce network parameters while maximizing SISR results. LFFN is built on spindle blocks and a softmax feature fusion module (SFFM). Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit. The dimension extension layer expands low dimension to high dimension and implicitly learns the feature maps which is suitable for the next unit. The feature exploration unit performs linear and nonlinear feature exploration aimed at different feature maps. The feature refinement layer is used to fuse and refine features. SFFM fuses the features from different modules in a self-adaptive learning manner with softmax function, making full use of hierarchical information with a small amount of parameter cost. Both qualitative and quantitative experiments on benchmark datasets show that LFFN achieves favorable performance against state-of-the-art methods with similar parameters.

Liping Zhang, Zongqing Lu, Qingmin Liao

The convolutional neural network model for optical flow estimation usually outputs a low-resolution(LR) optical flow field. To obtain the corresponding full image resolution,interpolation and variational approach are the most common options, which do not effectively improve the results. With the motivation of various convolutional neural network(CNN) structures succeeded in single image super-resolution(SISR) task, an end-to-end convolutional neural network is proposed to reconstruct the high resolution(HR) optical flow field from initial LR optical flow with the guidence of the first frame used in optical flow estimation. Our optical flow super-resolution(OFSR) problem differs from the general SISR problem in two main aspects. Firstly, the optical flow includes less texture information than image so that the SISR CNN structures can't be directly used in our OFSR problem. Secondly, the initial LR optical flow data contains estimation error, while the LR image data for SISR is generally a bicubic downsampled, blurred, and noisy version of HR ground truth. We evaluate the proposed approach on two different optical flow estimation mehods and show that it can not only obtain the full image resolution, but generate more accurate optical flow field (Accuracy improve 15% on FlyingChairs, 13% on MPI Sintel) with sharper edges than the estimation result of original method.