Current text-to-image models face challenges in visual text rendering: text encoders like CLIP and T5 lack glyph-level understanding and often struggle to distinguish between the specific words to be rendered and their intended semantic meaning within prompts. In addition, inconsistencies between the base model and its plugins further compromise the quality of synthesized images. In this paper, we enhance the existing text-to-image method by addressing the following aspects: (1) Text-Glyph Alignmentin a Visual Question Answering (VQA) manner to enable glyph understanding for the text encoder. This involves establishing an explicit alignment between the representations of the glyphs and their detailed attribute descriptions, which boosts the model's ability to capture fine-grained visual features of the text. (2) Accurate and harmony visual text rendering: integrating pre-aligned glyph-visual embeddings with semantic text tokens through the Multimodal Diffusion Transformer(MMDiT) synchronously, ensuring coherent feature alignment and enhancing both the robustness and fidelity of visual text rendering. (3) Image Aesthetic Refinement: leveraging a multisource data training strategy that incorporates diverse, high-quality image-text pairs from various domains, exposing the model to extensive linguistic and visual diversity while maintaining superior aesthetic quality throughout training. Our experiments demonstrate that the proposed approach significantly outperforms the existing state-of-the-art method.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
The Structure-Equivalent Prior: Unifying Temporal Dynamics and 3D Evolution in 4D Latent Space
PDF ↗Recent advances in deep learning-based 3D representation have achieved remarkable success, particularly in modeling static high-fidelity geometries. However, the extension of these techniques to dynamic 3D scenes introduces a critical challenge of effectively representing spatio-temporal dependencies, i.e., jointly modeling detailed spatial structures within frames and temporal dynamics across frames. To address this challenge, this paper proposes that the temporal evolution observed in dynamic 3D scenes is fundamentally attributable to the deformation of underlying spatial structures. To capture this relationship, we introduce a unified continuous 4D latent space representation incorporating a structure-equivalence prior, named SEP-4D. The core of SEP-4D is an efficient 4D tensor decomposition-fusion approach. This method fuses decomposed learnable 2D feature planes via a plane-wise spatio-temporal fusion mechanism of planar distributions, explicitly enforcing the principle that temporal evolution originates from geometric deformations of the 3D structure. To mitigate the associated computational demands, we sample the 3D probability volumes generated by VAE-based fusion into a spatio-temporally consistent 4D latent representation. The efficacy of our approach is validated through experiments on the fundamental task of 4D occupancy reconstruction. Extensive results demonstrate that, by leveraging the inherent equivalence of temporal dynamics and structural deformation, our method achieves high-quality reconstruction across various sequence lengths. Notably, for 4-frame scenes, we attain an impressive 91.68% mIoU, significantly outperforming state-of-the-art baselines on standard benchmarks.
Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and resource constraints during both training and inference. Although recent training-free approaches have alleviated resource demands by compressing visual features, their reliance on incomplete visual information limits the performance potential. To address these limitations, we propose Adaptive Pivot Visual information Retrieval (APVR), a training-free framework that hierarchically retrieves and retains sufficient and important visual information. It breakthroughs the memory wall limitation via two complementary components: Pivot Frame Retrieval employs query expansion and iterative spatio-semantic confidence scoring to identify relevant video frames, and Pivot Token Retrieval performs query-aware attention-driven token selection within up to 1024 pivot frames. This dual granularity approach enables the processing of hour-long videos while maintaining semantic fidelity. Experimental validations on three different baseline MLLMs demonstrate significant performance improvements up to 9.5%, 4.6% and 9.7% on LongVideoBench, VideoMME and MLVU, respectively. APVR achieves state-of-the-art results for both training-free and training-based approaches.
Accurately forecasting the spatiotemporal dynamics of biological systems, such as human pluripotent stem cell (hPSC)-derived cardiac organoids, from microscopy time-series is a critical challenge in biomedicine with profound implications for drug discovery. Existing generative models often fail to capture the intricate dynamics of organoid development, struggling with their irregular morphology, indistinct boundaries, and complex spatiotemporal patterns. To overcome these limitations, we introduce OrgaCast, a novel multimodal conditional diffusion model for high-fidelity organoid forecasting. OrgaCast uniquely conditions the generative process on three synergistic modalities: (i) historical image sequences, captured by a dedicated spatiotemporal control module; (ii) structured numerical metadata defining experimental conditions; and (iii) descriptive text captions summarizing the biological context. This comprehensive conditioning enables the generation of forecasts with high visual accuracy and biological plausibility. Furthermore, to enhance the model's utility in critical research settings, we introduce a post-hoc uncertainty quantification method that produces intuitive confidence maps, bolstering the interpretability and trustworthiness of predictions. Extensive experiments on a challenging cardiac organoid dataset demonstrate that OrgaCast outperforms baselines in metrics such as SSIM, PSNR, and LPIPS. Our framework presents a robust solution for biological forecasting, promising to accelerate research discovery while minimizing experimental costs and manual effort.
Universal visual anomaly detection aims to identify anomalies from novel or unseen vision domains without additional fine-tuning, which is critical in open scenarios. Recent studies have demonstrated that pre-trained vision-language models like CLIP exhibit strong generalization with just zero or a few normal images. However, existing methods struggle to design prompt templates, handle complex token interactions, or require fine-tuning on target domains, resulting in limited flexibility. In this work, we present a simple yet effective AdaptCLIP based on two key insights. First, adaptive visual and textual representations should be learned alternately rather than jointly. Second, comparative learning between query and normal image prompt should incorporate both contextual and aligned residual features, rather than relying solely on residual features. AdaptCLIP treats CLIP models as a foundational service, adding only three simple adapters, visual adapter, textual adapter, and prompt-query adapter, at its input or output ends. AdaptCLIP supports zero-/few-shot generalization across domains and provides a training-free approach on target domains once trained on a base dataset. AdaptCLIP achieves state-of-the-art performance on 12 anomaly detection benchmarks from industrial and medical domains, significantly outperforming existing competitive methods.
The proliferation of generative image models has revolutionized AIGC creation while amplifying concerns over content provenance and manipulation forensics. Existing methods are typically either unable to localize tampering or restricted to specific generative settings, limiting their practical utility. We propose GenPTW, a General watermarking framework that unifies Provenance tracing and Tamper localization in latent space. It supports both in-generation and post-generation embedding without altering the generative process, and is plug-and-play compatible with latent diffusion models (LDMs) and visual autoregressive (VAR) models. To achieve precise provenance tracing and tamper localization, we embed the watermark using two complementary mechanisms: cross-attention fusion aligned with latent semantics and spatial fusion providing explicit spatial guidance for edit sensitivity. A tamper-aware extractor jointly conducts provenance tracing and tamper localization by leveraging watermark features together with high-frequency features. Experiments show that GenPTW maintains high visual fidelity and strong robustness against diverse AIGC-editing.
DeFB: Decomposed Feature Learning for Real-Time Multi-Person Eyeblink Detection in Untrimmed In-the-Wild Videos
PDF ↗Multi-person eyeblink detection in untrimmed in-the-wild videos is a recently emerged and challenging task. Due to its significant spatio-temporal fine-grained characteristics compared to general actions, we empirically find that general action detectors, though effective in general domains, struggle with this task (i.e., Blink-AP < 2%). Specialized eyeblink detection methods alleviate it through fine-grained spatio-temporal operations. SOTA method proposes a unified model combining instance-aware face localization and eyeblink detection through joint multi-task learning and feature sharing. While effective, it exhibits two critical limitations that may contribute to its unsatisfactory performance (i.e., Blink-AP=10.11%): (1) Face localization and eyeblink detection require distinct spatio-temporal feature granularities, making joint modeling in a unified feature space suboptimal. (2) Eyeblink task training could be largely affected by unstable face-eye feature learning under the joint training paradigm. To address this, we propose DeFB, a decomposed feature learning paradigm with favorable effectiveness and efficiency: (1) We model faces and eyes in granularity-specific feature spaces, which enhances fine-grained perception while reducing computational costs compared to a unified feature space. (2) To mitigate face-eye feature learning instability, we adopt an asynchronous learning mechanism where eye feature learning refines well-trained coarse face features, with shared queries acting as a bridge between stages to retain the efficient feature sharing of existing unified models. Compared with SOTA method, DeFB doubles the performance (Blink-AP: 24.65% v.s. 10.11%) while boosting efficiency by nearly 35%. DeFB can also be integrated as a plug-in to substantially augment the eyeblink detection capabilities of general action detectors.
Egocentric human pose estimation (HPE) plays a crucial role in immersive applications such as virtual and augmented reality. However, existing methods relying on either visual or sparse inertial data alone often suffer from occlusion or ill-posed problems. In this work, we propose SAME, a novel spatial-aware multimodal fusion framework combining the complementary signals from the stereo images and sparse IMUs for accurate and robust egocentric HPE. It adopts a two-stage network based on a dual coordinate frame to mitigate the coordinate inconsistencies among the stereo cameras and the IMUs. In the first stage, the IMU signals are transformed into the local frame and iteratively fused with the stereo images for estimating 3D poses in the local frame. In the second stage, the local poses are transformed into the global frame with the 6DOF head poses provided by the head-mounted display's (HMD) SLAM algorithm and then temporally aggregated via a temporal Transformer network. Meanwhile, to achieve geometric and semantic alignment among multi-modal features, we present a depth-guided spatial-aware deformable stereo attention network and a modality-aware Transformer decoder for cross-view and cross-modal feature fusion. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on the public EMHI multi-modal egocentric pose estimation benchmark.
Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the reliability of pseudo-labels. Hence, we develop a semi-supervised framework, namely DerProp, equipped with a novel derivative label propagation to rectify imperfect pseudo-labels. Our label propagation method imposes discrete derivative operations on pixel-wise feature vectors as additional regularization, thereby generating strictly regularized similarity metrics. Doing so effectively alleviates the ill-posed problem that identical similarities correspond to different features, through constraining the solution space. Extensive experiments are conducted to verify the rationality of our design, and demonstrate our superiority over other methods.
Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers
PDF ↗Multi-modal learning integrating medical images and tabular data has significantly advanced clinical decision-making in recent years. Self-Supervised Learning (SSL) has emerged as a powerful paradigm for pretraining these models on large-scale unlabeled image-tabular data, aiming to learn discriminative representations. However, existing SSL methods for image-tabular representation learning are often confined to specific data cohorts, mainly due to their rigid tabular modeling mechanisms when modeling heterogeneous tabular data. This inter-tabular barrier hinders the multi-modal SSL methods from effectively learning transferrable medical knowledge shared across diverse cohorts. In this paper, we propose a novel SSL framework, namely CITab, designed to learn powerful multi-modal feature representations in a cross-tabular manner. We design the tabular modeling mechanism from a semantic-awareness perspective by integrating column headers as semantic cues, which facilitates transferrable knowledge learning and the scalability in utilizing multiple data sources for pretraining. Additionally, we propose a prototype-guided mixture-of-linear layer (P-MoLin) module for tabular feature specialization, empowering the model to effectively handle the heterogeneity of tabular data and explore the underlying medical concepts. We conduct comprehensive evaluations on Alzheimer's disease diagnosis task across three publicly available data cohorts containing 4,461 subjects. Experimental results demonstrate that CITab outperforms state-of-the-art approaches, paving the way for effective and scalable cross-tabular multi-modal learning.
Anchor-based 3D Gaussian Splatting (GS), exemplified by Scaffold-GS, achieves remarkable storage efficiency through a hybrid explicit-implicit representation. However, their reliance on a single, monolithic network to decode anchor features imposes a severe bottleneck on model capacity, often resulting in blurred details and view-dependent artifacts in complex scenes. To break this bottleneck, we introduce the concept of Scene Experts: a strategy that decomposes the task of modeling a complex scene across a collection of specialized sub-models. To realize the paradigm, we propose MoE-GS. Our approach designs the decoder as a Sparsely-Gated Mixture of Experts (MoE), which dramatically increases the model's total capacity while maintaining comparable inference cost via sparse activation. To effectively train this high-capacity model, we propose two key innovations: (1) A progressive curriculum learning strategy that first trains all experts on a robust baseline before encouraging them to specialize on different scene components. (2) A novel opacity-aware regularization that penalizes inactive neural Gaussians, ensuring the expanded capacity is efficiently used. Extensive experiments demonstrate that MoE-GS substantially outperforms state-of-the-art methods on diverse benchmarks, significantly improving reconstruction fidelity while requiring a smaller or comparable Gaussian model size.
OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding
PDF ↗LVLMs have been shown to perform excellently in image-level tasks such as VQA and caption. However, in many instance-level tasks, such as visual grounding and object detection, LVLMs still show performance gaps compared to previous expert models. Meanwhile, although pedestrian tracking is a classical task, there have been a number of new topics in combining object tracking and natural language, such as Referring MOT, Cross-view Referring MOT, and Semantic MOT. These tasks emphasize that models should understand the tracked object at an advanced semantic level, which is exactly where LVLMs excel. In this paper, we propose a new unified Pedestrian Tracking framework, namely OmniPT, which can track, track based on reference and generate semantic understanding of tracked objects interactively. We address two issues: how to model the tracking task into a task that foundation models can perform, and how to make the model output formatted answers. To this end, we implement a training phase consisting of RL-Mid Training-SFT-RL. Based on the pre-trained weights of the LVLM, we first perform a simple RL phase to enable the model to output fixed and supervisable bounding box format. Subsequently, we conduct a mid-training phase using a large number of pedestrian-related datasets. Finally, we perform supervised fine-tuning on several pedestrian tracking datasets, and then carry out another RL phase to improve the model's tracking performance and enhance its ability to follow instructions. We conduct experiments on tracking benchmarks and the experimental results demonstrate that the proposed method can perform better than the previous methods.
This paper addresses the challenge of estimating local surface differential properties, specifically surface normals and curvatures, from raw 3D point clouds. Traditional methods either rely on fitting pre-defined analytic surfaces risking model bias, or directly regress normals and curvatures overlooking their intrinsic geometric correlation. We propose a learning-based approach that locally fits osculating implicit quadrics to recover both normals and curvatures simultaneously. Drawing on classical differential geometry, we exploit the fact that every point on a C² surface admits an osculating quadric in Monge form that exactly reproduces local differential properties. However, the Monge frame itself depends on the very differential quantities being estimated. To bypass this circularity, we reformulate the Monge-form quadric as an implicit representation in a canonical local frame derived solely from point coordinates, enabling supervised learning without requiring Monge frame alignment. This reformulation allows us to construct a ground-truth dataset of such local-frame quadrics and train a neural network to predict per-point weights and offsets for a robust weighted least squares fitting process. The learned offsets account for the deviations of neighboring points from the idealized osculating surface. We further incorporate stable curvature formulations into the training loss alongside normal supervision to enhance estimation fidelity. Extensive experiments on diverse datasets demonstrate that our method outperforms prior approaches in normal and curvature estimation from raw point clouds.
Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more robust in various weather conditions and can detect point-wise velocity, making it a valuable complement to LiDAR. However, radar inputs pose challenges due to noise, low resolution, and sparsity. Moreover, there is currently no dataset that combines LiDAR and radar data specifically for scene flow estimation. To address this gap, we construct a Radar-LiDAR scene flow dataset based on a public real-world automotive dataset. We propose an effective preprocessing strategy for radar denoising and scene flow label generation, deriving more reliable flow ground truth for radar points out of the object boundaries. Additionally, we introduce RaLiFlow, the first joint scene flow learning framework for 4D radar and LiDAR, which achieves effective radar-LiDAR fusion through a novel Dynamic-aware Bidirectional Cross-modal Fusion (DBCF) module and a carefully designed set of loss functions. The DBCF module integrates dynamic cues from radar into the local cross-attention mechanism, enabling the propagation of contextual information across modalities. Meanwhile, the proposed loss functions mitigate the adverse effects of unreliable radar data during training and enhance the instance-level consistency in scene flow predictions from both modalities, particularly for dynamic foreground areas. Extensive experiments on the repurposed scene flow dataset demonstrate that our method outperforms existing LiDAR-based and radar-based single-modal methods by a significant margin.
Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm, focusing on independent object localization and editing while neglecting critical inter-object interactions. However, this work points out that the neglected attention entanglements in inter-object conflict regions, inherently hinder disentangled multi-object editing, leading to either inter-object editing leakage or intra-object editing constraints. We thereby propose a novel multi-layer disentangled editing framework LayerEdit, a training-free method which, for the first time, through precise object-layered decomposition and coherent fusion, enables conflict-free object-layered editing. Specifically, LayerEdit introduces a novel “decompose-editing-fusion” framework, consisting of: (1) Conflict-aware Layer Decomposition module, which utilizes an attention-aware IoU scheme and time-dependent region removing, to enhance conflict awareness and suppression for layer decomposition. (2) Object-layered Editing module, to establish coordinated intra-layer text guidance and cross-layer geometric mapping, achieving disentangled semantic and structural modifications. (3) Transparency-guided Layer Fusion module, to facilitate structure-coherent inter-object layer fusion through precise transparency guidance learning. Extensive experiments verify the superiority of LayerEdit over existing methods, showing unprecedented intra-object controllability and inter-object coherence in complex multi-object scenarios.
MOGO: Residual Quantized Hierarchical Causal Transformer for Real-Time and Infinite-Length 3D Human Motion Generation
PDF ↗Recent advances in transformer-based text-to-motion generation have significantly improved motion quality. However, achieving both real-time performance and long-horizon scalability remains an open challenge. In this paper, we present MOGO (Motion Generation with One-pass), a novel autoregressive framework for efficient and scalable 3D human motion generation. MOGO consists of two key components. First, we introduce MoSA-VQ, a motion scale-adaptive residual vector quantization module that hierarchically discretizes motion sequences through learnable scaling parameters, enabling dynamic allocation of representation capacity and producing compact yet expressive multi-level representations. Second, we design the RQHC-Transformer, a residual quantized hierarchical causal transformer that decodes motion tokens in a single forward pass. Each transformer block aligns with one quantization level, allowing hierarchical abstraction and temporally coherent generation with strong semantic flow. Compared to diffusion- and LLM-based approaches, MOGO achieves lower inference latency while preserving high motion fidelity. Moreover, its hierarchical latent design enables seamless and controllable infinite-length motion generation, with stable transitions and the ability to adaptively incorporate updated control signals at arbitrary points in time. To further enhance generalization and interpretability, we introduce Textual Condition Alignment (TCA), which leverages large language models with Chain-of-Thought reasoning to bridge the gap between real-world prompts and training data. TCA not only improves zero-shot performance on unseen datasets but also enriches motion comprehension for in-distribution prompts through explicit intent decomposition. Extensive experiments on HumanML3D, KIT-ML, and the unseen CMP dataset demonstrate that MOGO outperforms prior methods in generation quality, inference efficiency, and temporal scalability.
DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment
PDF ↗Blind Image Quality Assessment, aiming to replicate human perception of visual quality without reference, plays a key role in vision tasks, yet existing models often fail to effectively capture subtle distortion cues, leading to a misalignment with human subjective judgments. We identify that the root cause of this limitation lies in the lack of reliable distortion priors, as methods typically learn shallow relationships between unified image features and quality scores, resulting in their insensitive nature to distortions and thus limiting their performance. To address this, we introduce DR.Experts, a novel prior-driven BIQA framework designed to explicitly incorporate distortion priors, enabling a reliable quality assessment. DR.Experts begins by leveraging a degradation-aware vision-language model to obtain distortion-specific priors, which are further refined and enhanced by the proposed Distortion-Saliency Differential Module through distinguishing them from semantic attentions, thereby ensuring the genuine representations of distortions. The refined priors, along with semantics and bridging representation, are then fused by a proposed mixture-of-experts style module named the Dynamic Distortion Weighting Module. This mechanism weights each distortion-specific feature as per its perceptual impact, ensuring that the final quality prediction aligns with human perception. Extensive experiments conducted on five challenging BIQA benchmarks demonstrate the superiority of DR.Experts over current methods and showcase its excellence in terms of generalization and data efficiency.
Human artists can continuously refine their coarse sketches during artistic creation. This is quite different from existing autoregressive generation, where a token is determined once sampled. Aiming to flexibly refine the generated contents, this paper presents a Self-Calibrated AutoregressioN (SCAN) model capable of self-evaluating and refining generation quality without regenerating the entire image. We unify image token generation and quality evaluation into a single autoregressive model, formulating both tasks as categorical prediction problems. During inference, the model first generates a coarse initial image, then iteratively refines the lowest-quality patches until satisfactory image quality is achieved. Experimental results demonstrate that SCAN effectively handles diverse real-world generation errors and achieves a promising balance between image quality and speed. For example, SCAN-XL achieves an FID of 2.10 and an IS of 326.1, surpassing the LlamaGen-XL by 1.29 (+38%) in FID and 99.0 (+43.6%) in IS, with a 5.6× speedup (19.76s to 3.56s). Compared to recent works, SCAN improves FID and speed by +18.3% and +23% over VAR-d20, and by +7% and +46% over RandAR-XL.
We present ElastoGen, a knowledge-driven AI model that generates physically accurate 4D elastodynamics. Unlike deep models that learn from video- or image-based observations, ElastoGen leverages the principles of physics and learns from established mathematical and optimization procedures. The core idea of ElastoGen is converting the differential equation, corresponding to the nonlinear force equilibrium, into a series of iterative local convolution-like operations, which naturally fit deep architectures. We carefully build our network module following this overarching design philosophy. ElastoGen is much more lightweight in terms of both training requirements and network scale than deep generative models. Because of its alignment with actual physical procedures, ElastoGen efficiently generates accurate dynamics for a wide range of hyperelastic materials and can be easily integrated with upstream and downstream deep modules to enable end-to-end 4D generation.
IE-SRGS: An Internal-External Knowledge Fusion Framework for High-Fidelity 3D Gaussian Splatting Super-Resolution
PDF ↗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.