Reconstructing high-resolution (HR) 3D Gaussian Splatting (3DGS) models from low-resolution (LR) inputs remains challenging due to the lack of fine-grained textures and geometry. Existing methods typically rely on pre-trained 2D super-resolution (2DSR) models to enhance textures, but suffer from 3D Gaussian ambiguity arising from cross-view inconsistencies and domain gaps inherent in 2DSR models. We propose IE-SRGS, a novel 3DGS SR paradigm that addresses this issue by jointly leveraging the complementary strengths of external 2DSR priors and internal 3DGS features. Specifically, we use 2DSR and depth estimation models to generate HR images and depth maps as external knowledge, and employ multi-scale 3DGS models to produce cross-view consistent, domain-adaptive counterparts as internal knowledge. A mask-guided fusion strategy is introduced to integrate these two sources and synergistically exploit their complementary strengths, effectively guiding the 3D Gaussian optimization toward high-fidelity reconstruction. Extensive experiments on both synthetic and real-world benchmarks show that IE-SRGS consistently outperforms state-of-the-art methods in both quantitative accuracy and visual fidelity.

Zero-shot EEG-to-image retrieval aims to decode perceived visual content from electroencephalography (EEG) by aligning neural responses with pretrained visual representations, providing a promising route toward scalable visual neural decoding and practical brain-computer interfaces. However, robust EEG-to-image retrieval remains challenging, because prior methods usually rely on either a single fixed visual target or a subject-invariant target construction scheme. Such designs overlook two important properties of visually evoked EEG signals: they preserve information across multiple representational scales, and the visual granularity best matched to EEG may vary across subjects. To address these issues, subject-aware multi-granularity alignment (SAMGA) framework is proposed for zero-shot EEG-to-image retrieval. SAMGA first constructs a subject-aware visual supervision target by adaptively aggregating multiple intermediate representations from a pretrained vision encoder, allowing the model to absorb subject-dependent granularity deviations during training while preserving subject-agnostic inference. Building on this adaptive target construction, a coarse-to-fine cross-modal alignment strategy is further designed with a shared encoder wherein the coarse stage stabilizes the shared semantic geometry and reduces subject-induced distribution shift, and the fine stage further improves instance-level retrieval discrimination. Extensive experiments on the THINGS-EEG benchmark demonstrate that the proposed method achieves 91.3

3D Gaussian Splatting has emerged as a significant algorithm for novel view synthesis, with many studies applying it to dynamic scenes, such as using deformed MLPs for motion prediction. However, existing methods often overlook contextual information in time series, leading to inaccuracies in motion modeling. To address this, we propose the KF-GS method, inspired by the Kalman Filter, which combines observation and prediction to estimate the state of dynamic systems. We model the motion field as local linear transformations, using the motion state from the previous frame to predict the current frame’s motion. By adjusting the deformed MLP observations with the predicted values, our approach integrates information from the previous frame into the current motion state, enhancing accuracy. To ensure reliable information from the previous frame, we employ an adaptive training strategy and adaptive smoothing constraint regularization. As training progresses, we reduce the impact of predicted values to correct for potential errors in dynamic predictions. We conduct experiments on real and synthetic datasets. Compared to previous methods, our KF-GS achieves state-of-the-art performance in novel view synthesis, offering better visual coherence and maintaining high rendering speed.

High-resolution volumetric medical imaging is critical for clinical diagnosis, yet acquisition is often limited by scanner hardware, scan time, and for CT, radiation dose. Medical 3D Super-Resolution (Med3DSR) offers a computational alternative, but existing methods commonly rely on per-subject optimization, pretrained priors, or coordinate-based implicit representations, which compromise anatomical fidelity and limit efficiency. To address these limitations, we present MedGSSR, a fully end-to-end feed-forward framework that represents volumes as an explicit 3D Gaussian field for Med3DSR. Unlike coordinate-based implicit functions, our explicit 3D Gaussian representation naturally enhances signal continuity and local high-frequency fidelity. Specifically, MedGSSR explicitly decouples the reconstruction process into coarse-grained structural preservation and fine-grained textural refinement through the proposed Pyramid Anatomical Encoder and a Hierarchical Gaussian Projector. To support arbitrary-scale super-resolution, we introduce sub-voxel Gaussian decomposition and a Differentiable Gaussian Voxelizer that directly queries the continuous 3D intensity field, reducing discretization artifacts. Extensive experiments on MRI and CT benchmarks demonstrate that MedGSSR significantly outperforms state-of-the-art methods. Notably, our framework exhibits robust generalizability across unseen datasets without requiring per-subject optimization, enabling fast inference and high-fidelity volumetric super-resolution in practical clinical settings. Our project webpage, including code, is at https://william2ai.github.io/medgssr

Recent text-to-image (T2I) diffusion models have made significant strides in generating high-quality images from diverse textual prompts. Despite this progress, these models often face challenges in accurately understanding and synthesizing complex prompts, primarily due to their limited compositional capabilities. In this study, we propose a novel approach for compositional T2I synthesis using layout-guided diffusion models, which do not require additional training. Specifically, we leverage the chain-of-code prompting technique of large language models to interpret textual prompts and generate object layouts with spatial coherence. To enhance the alignment between generated images and textual descriptions, we introduce two innovative layout-guided loss functions: Patch-oriented Cross-Attention (PCA) loss and Region-oriented Cross-Attention (RCA) loss. The PCA loss emphasizes high activation values for image patches that attend to all tokens in the prompt across the layout. The RCA loss enhances the average attention within the layout, thereby increasing the accuracy of generating objects and their associated attributes within specified regions. These proposed loss functions reassign cross-attention in diffusion models during the denoising process. Our comprehensive experiments consistently demonstrate the effectiveness of our approach in improving semantic alignment between generated images and a diverse range of textual prompts, while ensuring high usability as a ready-to-use plugin.

3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images. Existing methods rely on dense LR inputs and per-scene optimization, which restricts the high-frequency priors for constructing HR 3D Gaussian Splatting (3DGS) to those inherited from pretrained 2D super-resolution (2DSR) models. This severely limits reconstruction fidelity, cross-scene generalization, and real-time usability. We propose to reformulate 3DSR as a direct feed-forward mapping from sparse LR views to HR 3DGS representations, enabling the model to autonomously learn 3D-specific high-frequency geometry and appearance from large-scale, multi-scene data. This fundamentally changes how 3DSR acquires high-frequency knowledge and enables robust generalization to unseen scenes. Specifically, we introduce \textbf{SR3R}, a feed-forward framework that directly predicts HR 3DGS representations from sparse LR views via the learned mapping network. To further enhance reconstruction fidelity, we introduce Gaussian offset learning and feature refinement, which stabilize reconstruction and sharpen high-frequency details. SR3R is plug-and-play and can be paired with any feed-forward 3DGS reconstruction backbone: the backbone provides an LR 3DGS scaffold, and SR3R upscales it to an HR 3DGS. Extensive experiments across three 3D benchmarks demonstrate that SR3R surpasses state-of-the-art (SOTA) 3DSR methods and achieves strong zero-shot generalization, even outperforming SOTA per-scene optimization methods on unseen scenes. Codes will be released upon publication.

Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information. However, existing methods often overlook personalized client performance and struggle with modality/task discrepancies, as well as model heterogeneity. To address these challenges, we propose FedAFD, a unified MFL framework that enhances client and server learning. On the client side, we introduce a bi-level adversarial alignment strategy to align local and global representations within and across modalities, mitigating modality and task gaps. We further design a granularity-aware fusion module to integrate global knowledge into the personalized features adaptively. On the server side, to handle model heterogeneity, we propose a similarity-guided ensemble distillation mechanism that aggregates client representations on shared public data based on feature similarity and distills the fused knowledge into the global model. Extensive experiments conducted under both IID and non-IID settings demonstrate that FedAFD achieves superior performance and efficiency for both the client and the server.

The application of face recognition (FR) has raised wide concerns on privacy leakage. Existing privacy-preserving methods often fail to effectively eliminate sensitive attributes, leaving residual information vulnerable to reconstruction attacks. In this paper, we propose a component-based perturbation method for enhancing the resistance of identity features against reconstruction while preserving the FR utility. We first evaluate the importance of facial components using class activation map (CAM) and face parsing. Second, we propose a channelwise differentiate filtering strategy and utilize CAM to guide the generation of perturbations in the frequency domain. Finally, we optimize our model with a multi-task loss. Experiments on public datasets show that our method achieves an effective balance among maintaining FR utility, concealing visual information, and resisting reconstruction attacks.

Recently, 3D Gaussian Splatting (3DGS) based methods, such as Scaffold-GS, have exhibited state-of-the-art performance for high-fidelity scene reconstruction. However, existing methods may suffer from degraded details because they usually pay the same attention to the whole image set and their contents. In fact, some parts of the image data may contain more information than others. Thus, it is reasonable to treat them differently. Motivated by this, in this paper, we propose a new 3DGS-based method to adaptively choose the data that are more valuable for training. Our method consists of two key parts: Adaptive Sampling (AS) and Region-based Rendering (RR). AS focuses on collecting difficult data for 3DGS training. RR focuses on enabling training with partial image data. Our method can produce more fine-grained details for scene reconstruction and has good scalability. On multiple public datasets, we verify the effectiveness of the proposed method by conducting comparative and ablation experiments. The quantitative and qualitative experimental results show that our method has achieved state-of-the-art results compared with the baselines.

Recent studies on 3D Gaussian splatting demonstrate promising applications in novel view synthesis using several posed images. These images captured in real-life scenarios may be blurry and lead to unsatisfactory synthesis quality. Utilizing 2D image deblurring models to sharpen the blurry image before 3D Gaussian splatting is a natural inspiration. However, directly applying 2D image deblurring models for novel view synthesis results in poor performance due to the inevitable inconsistencies. For the above problem, this paper introduces a new approach called view-consistent Gaussian splatting via alternating branch optimization strategy(VC-GS). VC-GS consists of two branches: preceding branch and subsequent branch. The preceding branch restores multi-view blurry inputs using a 2D deblurring model before 3D Gaussian splatting, while the subsequent branch directly applies 3D Gaussian splatting to the blurry inputs and restores the synthesized views with the same model. Through the alternating branch optimization of the preceding branch and subsequent branch, the 3D Gaussians in the preceding branch can achieve high-quality reconstruction and maintain view consistency under blurry inputs. To validate the effectiveness of the approach, we conducted qualitative and quantitative experiments on synthetic and real datasets, demonstrating that the proposed approach achieves better results. Our project page is available at https://github.com/DTG777/View-Consistent-Gaussian-Splatting-from-Blurry-Images-for-Novel-View-Synthesis .

Recent advances in 4D Gaussian Splatting have boosted dynamic scene reconstruction and real-time rendering. However, current methods remain retrospective, lacking the ability to forecast future states-limiting their utility in tasks like autonomous navigation and robotics. To address these limitations, we propose FutureGS, a novel Gaussian-based dynamic scene representation framework tailored for continuous 3D future scene prediction and view synthesis. FutureGS introduces a dual-domain decoupled representation, consisting of a static 3D Gaussian base to maintain spatial consistency and a dynamic deformation field to explicitly model temporal motion evolution. To capture long-range dependencies and complex motion dynamics, we design a multi-window collaborative prediction strategy that leverages a sliding temporal window and a bidirectional LSTM-based temporal encoder for robust future motion estimation. Furthermore, we propose a KNN-based local rigidity-aware fusion mechanism, which adaptively regulates the prediction consistency based on local deformation intensity, enhancing the geometric stability and physical plausibility of future scenes. Extensive experiments on standard dynamic scene benchmarks, including D-NeRF and NeRF-DS, demonstrate that FutureGS achieves superior performance in terms of visual fidelity and spatiotemporal consistency, enabling real-time and photorealistic rendering from arbitrary viewpoints at future time steps.

Point clouds are widely used across various domains, yet their unordered and unstructured nature presents challenges for lightweight models and real-time inference. This paper introduces ViewCloud, a novel multi-view point-cloud-like representation that integrates the advantages of 2D renderings and 3D point clouds while maintaining a compact and efficient structure. Unlike conventional 3D representations, ViewCloud explicitly preserves viewpoint-specific geometric and semantic features, ensuring high information density with minimal redundancy. To construct ViewCloud, we propose an adaptive sampling strategy that extracts contour and interior pixels from multi-view 2D renderings, capturing essential shape characteristics while reducing storage overhead. We further design a ViewCloud-based multi-view feature aggregation Network, incorporating a contrastive learning-based semantic alignment Loss to enhance cross-view consistency and improve 3D recognition. Additionally, we extend ViewCloud to cross-domain retrieval, leveraging it as an intermediate representation to bridge 2D images and 3D point clouds within a shared feature space. Experiments on three benchmark datasets demonstrate that ViewCloud surpasses state-of-the-art methods in 3D recognition and cross-domain retrieval while significantly reducing storage and computational costs. These results establish ViewCloud as a scalable, efficient, and generalizable 3D representation.

In modern lives, the rapid proliferation of Internet of Things (IoT) devices has made them indispensable tools for data collection and analysis across various domains. However, growing concerns over data ownership and privacy have hindered effective data sharing among IoT devices, leading to the persistent challenge of data silos. Federated Learning (FL) has emerged as a promising solution to this problem by enabling collaborative model training without direct data exchange. Despite its potential, FL faces two critical limitations: severe catastrophic forgetting for historical knowledge and inefficient average aggregation. To address these challenges, this paper proposes FedGA, an innovative FL framework that leverages cosine similarity-based weighted aggregation to enhance model convergence speed. Furthermore, FedGA incorporates a mechanism to memorize historical models, thereby significantly alleviating catastrophic forgetting. Extensive experiments on three public datasets validate the effectiveness of FedGA, demonstrating its superior performance in both accuracy and training efficiency compared to state-of-the-art methods. The results highlight FedGA’s capability to overcome the key shortcomings of existing FL approaches, making it a robust solution for practical IoT applications.

The unprecedented capture and application of face images raise increasing concerns on anonymization to fight against privacy disclosure. Most existing methods may suffer from the problem of excessive change of the identity-independent information or insufficient identity protection. In this paper, we present a new face anonymization approach by distracting the intrinsic and extrinsic identity attentions. On the one hand, we anonymize the identity information in the feature space by distracting the intrinsic identity attention. On the other, we anonymize the visual clues (i.e. appearance and geometry structure) by distracting the extrinsic identity attention. Our approach allows for flexible and intuitive manipulation of face appearance and geometry structure to produce diverse results, and it can also be used to instruct users to perform personalized anonymization. We conduct extensive experiments on multiple datasets and demonstrate that our approach outperforms state-of-the-art methods.

Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view geometric consistency. We revisit SRGS, a simple baseline that couples plug-in 2D SR priors with geometry-aware cross-view regularization, and observe that most subsequent advances follow the same paradigm, either strengthening prior injection, refining cross-view constraints, or modulating the objective. However, this shared structure is rarely formalized as a unified objective with explicit modules, limiting principled attribution of improvements and reusable design guidance. In this paper, we formalize SRGS as a unified modular framework that factorizes 3DGS SR into two components, prior injection and cross-view regularization, within a joint objective. This abstraction subsumes a broad family of recent methods as instantiations of the same recipe, enabling analysis beyond single-method innovation. Across five public benchmarks, we consolidate nine representative follow-up methods and trace reported improvements to specific modules and settings. Ablations disentangle the roles of priors and consistency, and stress tests under sparse-view input and challenging capture conditions characterize robustness. Overall, our study consolidates 3DGS SR into a coherent foundation and offers practical guidance for robust, comparable 3DGS SR methods.

Neural Radiance Fields (NeRF) have achieved great success in the task of synthesizing novel views that preserve the same resolution as the training views. However, it is challenging for NeRF to synthesize high-quality high-resolution novel views with low-resolution training data. To solve this problem, we propose a zero-shot super-resolution training framework for NeRF. This framework aims to guide the NeRF model to synthesize high-resolution novel views via single-scene internal learning rather than requiring any external high-resolution training data. Our approach consists of two stages. First, we learn a scene-specific degradation mapping by performing internal learning on a pretrained low-resolution coarse NeRF. Second, we optimize a super-resolution fine NeRF by conducting inverse rendering with our mapping function so as to backpropagate the gradients from low-resolution 2D space into the super-resolution 3D sampling space. Then, we further introduce a temporal ensemble strategy in the inference phase to compensate for the scene estimation errors. Our method is featured on two points: (1) it does not consume high-resolution views or additional scene data to train super-resolution NeRF; (2) it can speed up the training process by adopting a coarse-to-fine strategy. By conducting extensive experiments on public datasets, we have qualitatively and quantitatively demonstrated the effectiveness of our method.

The reconstruction of high-quality 3D clothed humans from monocular images or videos has gained popularity in recent years due to its significant practical applications. While several surveys have addressed the reconstruction of full-body parametric human models from images or videos, this survey specifically delves into the challenges and methodologies of reconstructing 3D clothed humans. It covers both pose-dependent and dynamic approaches to clothed human reconstruction. Regarding pose-dependent clothed human reconstruction from monocular images, we investigate methodologies that employ regression models trained on high-quality 3D scans to estimate human geometry with clothing. Additionally, we explore research leveraging texture priors within large-scale diffusion models to enhance the inference of human appearance in occluded or unseen areas. In terms of dynamic clothed human reconstruction from monocular and sparse multi-view videos, we analyze human modeling techniques utilizing neural radiance fields and 3D Gaussian representations, which employ deformation fields to capture human movements across frames. Furthermore, we provide an overview of the datasets and commonly used quantitative evaluation metrics in these studies. Finally, we conclude by discussing open issues and proposing future research directions in the realistic reconstruction of clothed humans, emphasizing areas that warrant additional investigation.

The issue of face privacy protection has aroused wide social concern along with the increasing applications of face images. The latest methods focus on achieving a good privacy-utility tradeoff so that the protected results can still be used to support the downstream computer vision tasks. However, they may suffer from limited flexibility in manipulating this tradeoff because the practical requirements may vary under different scenarios. In this paper, we present a novel recurrent latent representation reorganization (LReOrg) framework to deal with the problem. LReOrg relies on two key modules to deal with the privacy-utility tradeoff, where the first one is responsible for anonymizing the privacy sensitive information and the other is responsible for recovering the destroyed useful insensitive information according to user requirements. LReOrg is advantageous in: (a) enabling users to recurrently process fine-grained attributes; (b) providing flexible control over privacy-utility tradeoff by manipulating which attributes to anonymize or preserve using cross-modal keywords; and (c) eliminating the need of data annotations for network training. The experimental results on benchmark datasets have reported the superior ability of our approach for providing flexible protection on facial information.