AAAI 2026 Papers

Open-Vocabulary Object Detection (OVOD) shows promise in remote sensing (RS), but due to its unique value, there are challenges such as the predominance of background regions, sparse labels, limited semantic information, and difficulties in semi-supervised training. To tackle these challenges, we propose the Semi-Supervised Open-Vocabulary Aerial Object Detection with Dual-Perception Prior Denoising (SOAR), which explicitly models the background embeddings of each scene to indirectly construct foreground priors, thereby capitalizing on the abundant background information present in RS imagery. We further introduce a query enhancement module that integrates language and foreground prior information to enhance the effectiveness of query selection and feature augmentation. During the decoding stage of semi-supervised training, we perform denoising and reconstruction of the foreground priors to generate pseudo-labels that support the training process. Additionally, we address the sparsity of label information through expansion and aggregation techniques, further improving model performance. Experimental evaluations reveal that, in the open-vocabulary object detection task on the DIOR dataset, our method achieves a mean Average Precision (mAP) of 68.5% and Harmonic Mean (HM) of 55.9%, outperforming the previous state-of-the-art model’s mAP of 61.6% and HM of 53.6%. Our approach offers a novel solution to the open-vocabulary challenge in aerial object detection.

Asymmetric image retrieval (AIR), which typically employs a compact model for the query side and a large model for the database server, has garnered significant attention in resource-constrained environments. While deep hashing methods have shown great potential in large-scale image retrieval, current attempts for the asymmetric image retrieval overlook the differences in quantization capabilities between query and gallery networks. In AIR, the conventional quantization scheme forces the outputs of small query models to approximate the discrete outputs of large models, imposing overly rigid and stringent constraints that severely limit the optimization of small query models. Furthermore, existing deep hashing methods for AIR necessitate labeled datasets from large models, which also limits their practical applicability. To this end, we reconsider the necessity of strict discretization in AIR and propose a novel asymmetric hashing method, named Deep Correlation Alignment Hashing (DCAH). Rather than explicitly quantizing continuous query features to match discrete gallery representations, we distill the correlation across both models and introduce a Correlation Alignment based Quantization (CAQ) scheme, thereby implicitly accomplishing quantization. To preserve the similarity consistency between the query and gallery models, we further employ a correlation alignment-based knowledge distillation strategy which is intrinsically compatible with the CAQ. Notably, the proposed quantization scheme can function as a plug-and-play module that seamlessly integrates with existing AIR methods. Comprehensive evaluations on three real-world benchmark datasets demonstrate the effectiveness of the proposed quantization scheme CAQ, and also show that DCAH achieves state-of-the-art performance in asymmetric image retrieval scenarios.

Accurate feature matching between image pairs is fundamental for various computer vision applications. In detector-base process, the feature matcher aims to find the optimal feature correspondences, and the match filter is used for further removing mismatches. However, their connection is rarely exploited since they are usually treated as two separate issues in previous method, which may lead to suboptimal results. In this paper, we propose an end-to-end collaborative feature matching (CFM) method, which contains a keypoint learning (KL) module and a correspondence learning (CL) module, to bridge the gap between two types of works. The former improves the discrimination of keypoints, and provides high-quality dynamic matches for CL module. The latter further captures the rich context of matches, and gives effective feedback to KL module. These two modules can reinforce each other in a progressive manner. Besides, we develop an efficient version of CFM, named ECFM, using an adaptive sampling strategy to avoid the negative influence of uninformative keypoints. Experimental results indicate that both methods outperform the state-of-the-art competitors in the tasks of relative pose estimation and visual localization.

Action recognition using uncrewed aerial vehicles (UAVs) faces unique challenges due to substantial view variations along the vertical spatial axis. Unlike ground-based scenarios, UAVs capture actions from diverse altitudes, resulting in pronounced appearance discrepancies and reduced recognition robustness. To address this, we introduce a multi-view formulation tailored for UAV altitudes and empirically uncover a distinctive partial order among views, where recognition accuracy consistently declines as altitude increases. This key observation motivates the proposed Aero Partial Order Guided Network (Aerorder), which explicitly models and exploits the hierarchical structure of UAV views to enhance cross-altitude action recognition. Aerorder comprises three main components: (1) a View Partition (VP) module that groups views by altitude using the head-to-body ratio; (2) an Order-aware Feature Decoupling (OFD) module that disentangles action-relevant and view-specific representations under partial order guidance; and (3) an Action Partial Order Guide (APOG) that progressively transfers knowledge from easier (low-altitude) to harder (high-altitude) views. Extensive experiments on Drone-Action, MOD20, and UAV validate the superiority of Aerorder, achieving consistent improvements over state-of-the-art methods, up to 4.7% and 1.3% gains on Drone-Action and MOD20, respectively.

Transferring 2D textures onto complex 3D scenes plays a vital role in enhancing the efficiency and controllability of 3D multimedia content creation. However, existing 3D style transfer methods primarily focus on transferring abstract artistic styles to 3D scenes. These methods often overlook the geometric information of the scene, which makes it challenging to achieve high-quality 3D texture transfer results. In this paper, we present GT2-GS, a geometry-aware texture transfer framework for gaussian splatting. First, we propose a geometry-aware texture transfer loss that enables view-consistent texture transfer by leveraging prior view-dependent feature information and texture features augmented with additional geometric parameters. Moreover, an adaptive fine-grained control module is proposed to address the degradation of scene information caused by low-granularity texture features. Finally, a geometry preservation branch is introduced. This branch refines the geometric parameters using additionally bound Gaussian color priors, thereby decoupling the optimization objectives of appearance and geometry. Extensive experiments demonstrate the effectiveness and controllability of our method. Through geometric awareness, our approach achieves texture transfer results that better align with human visual perception.

In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely constrained by the lack of large-scale 4D datasets, preventing models from adequately learning the critical spatial-temporal features necessary for high-quality 4D generation, thus hindering progress in this domain. To combat this, we propose a novel framework that transfers rich spatial priors from existing 3D diffusion models and temporal priors from video diffusion models to enhance 4D synthesis. We develop a spatial-temporal-disentangled 4D (STD-4D) Diffusion model, which synthesizes 4D-aware videos through disentangled spatial and temporal latents. To facilitate the best feature transfer, we design a novel Orthogonal Spatial-temporal Distributional Transfer (Orster) mechanism, where the spatiotemporal feature distributions are carefully modeled and injected into the STD-4D Diffusion. Further, during the 4D construction, we devise a spatial-temporal-aware HexPlane (ST-HexPlane) to integrate the transferred spatiotemporal features for better 4D deformation and 4D Gaussian feature modeling. Experiments demonstrate that our method significantly outperforms existing approaches, achieving superior spatial-temporal consistency and higher-quality 4D synthesis.

Multimodal change detection (MCD) has important applications in disaster assessment, but the nonlinear distortion of features and spatial misalignment caused by sensor imaging differences make it difficult to obtain changes through direct comparison. To overcome the above problems, this study aims to realize MCD by capturing the modality-independent structural commonality features between Multimodal Remote Sensing Images (MRSIs). To achieve this, we devise a basic Graph Kolmogorov-Arnold Network (GKAN) to excavate spatial structural relationships and cross-modal nonlinear mappings simultaneously. Based on this, we propose a Dual-branch GKAN (DGKAN) for unsupervised MCD, which can capture spatial-spectral structural commonality features and compare them directly to detect changes. Concretely, the GKAN is used within the DGKAN to build two autoencoders consisting of a Siamese encoder and two independent decoders to learn spatial-spectral structural commonality features through feature reconstruction. Besides, we introduce a Covariance Structural Commonality Loss (CSCL), which guides the network in extracting spatial-spectral structural commonality features between MRSIs by unsupervised constraints on the distributional consistency of cross-modal features. Experiments on several MCD datasets show that the proposed DGKAN can achieve convincing results, and ablation studies verify the effectiveness of the GKAN and CSCL.

Current adversarial examples (AEs) are typically designed for static models. However, with the wide application of Class-Incremental Learning (CIL), models are no longer static and need to be updated with new data distributed and labeled differently from the old ones. As a result, existing AEs often fail after CIL updates due to significant domain drift. In this paper, we propose SAE to enhance the sustainability of AEs against CIL. The core idea of SAE is to enhance the robustness of AE semantics against domain drift by making them more similar to the target class while distinguishing them from all other classes. Achieving this is challenging, as relying solely on the initial CIL model to optimize AE semantics often leads to overfitting. To resolve the problem, we propose a Semantic Correction Module. This module encourages the AE semantics to be generalized, based on a generative model capable of producing universal semantics. Additionally, it incorporates the CIL model to correct the optimization direction of the AE semantics, guiding them closer to the target class. To further reduce fluctuations in AE semantics, we propose a Filtering-and-Augmentation Module, which first identifies non-target examples with target-class semantics in the latent space and then augments them to foster more stable semantics. Comprehensive experiments demonstrate that SAE outperforms baselines by an average of 31.28% when updated with a 9-fold increase in the number of classes.

Despite the remarkable developments achieved by recent 3D generation works, scaling these methods to geographic extents, such as modeling thousands of square kilometers of Earth’s surface, remains an open challenge. We address this through a dual innovation in data infrastructure and model architecture. First, we introduce Aerial-Earth3D, the largest 3D aerial dataset to date, consisting of 50k curated scenes (each measuring 600m) captured across the U.S. mainland, comprising 45M multi-view Google Earth frames. Each scene provides pose-annotated multi-view images, depth maps, normals, semantic segmentation, and camera poses, with explicit quality control to ensure terrain diversity. Building on this foundation, we propose EarthCrafter, a tailored framework for large-scale 3D Earth generation via sparse-decoupled latent diffusion. Our architecture separates structural and textural generation: 1) Dual sparse 3D-VAEs compress high-resolution geometric voxels and textural 2D Gaussian Splats (2DGS) into compact latent spaces, largely alleviating the costly computation suffering from vast geographic scales while preserving critical information. 2) We propose condition-aware flow matching models trained on mixed inputs (semantics, images, or neither) to flexibly model latent geometry and texture features independently. Extensive experiments demonstrate that EarthCrafter performs substantially better in extremely large-scale generation. The framework further supports versatile applications, from semantic-guided urban layout generation to unconditional terrain synthesis, while maintaining geographic plausibility through our rich data priors from Aerial-Earth3D.

We introduce Daytime-Memory Guided Nighttime Image Enhancement (DMGNIE) framework, the first framework that turns long-running daytime surveillance videos of a single intersection into persistent “daytime memory” to guide nighttime image enhancement in traffic scenes. Our key insight is simple yet powerful: for a static scene, perfectly exposed daytime frames are, pixel-for-pixel, high-quality illumination prior for the same location under extreme low-light. Due to the complex lighting conditions in real-world traffic scenes, existing low-light image enhancement (LLIE) methods suffer from issues such as overexposure in highlight regions and noise amplification in low-light condition regions, which degrades the performance of downstream computer vision tasks. DMGNIE tackles these issues in two steps: (1) SegBMN, a semantic prior-based background modeling network, distills a clean, static daytime background from hours of video as scene prior guiding the enhancement of nighttime image; (2) a Foreground Localization-Guided Contrastive Learning module avoid the interference from the background prior with foreground objects during the guidance by maximizing the differences between foreground and background features. Finally, We conduct comprehensive experiments on real traffic surveillance datasets of two cities to evaluate the effectiveness. And the experimental results demonstrate that DMGNIE outperforms state-of-the-art baselines and achieves superior performance in challenging low-light conditions.

Dataset distillation has achieved remarkable progress as an effective approach for data compression. However, real-world data often comes from diverse domains, leading to potential mismatches between the domains of synthesized images and those of the evaluation set. Existing methods primarily assume domain alignment between them, which limits their generalization ability in the above cross-domain scenarios. In this paper, we aim to ensure that images synthesized from known domains maintain robust performance on unseen domains and propose a novel framework called Channel-masked Asymmetric Distribution Matching (CADM). During asymmetric distribution matching, domain-sensitive channels of real data are selectively masked at different layers to extract domain-invariant features that guide synthetic data optimization. To further improve synthetic data representation, we introduce a class-focused domain-agnostic regularization to capture class-relevant knowledge while ignoring domain-specific information. Experiments show that our method produces domain-robust synthetic data and substantially improves generalization performance on unseen domains.

Multi-object video motion transfer poses significant challenges for Diffusion Transformer (DiT) architectures due to inherent motion entanglement and lack of object-level control. We present MultiMotion, a novel unified framework that overcomes these limitations. Our core innovation is Mask-aware Attention Motion Flow (AMF), which utilizes SAM 2 masks to explicitly disentangle and control motion features for multiple objects within the DiT pipeline. Furthermore, we introduce RectPC, a high-order predictor-corrector solver for efficient and accurate sampling, particularly beneficial for multi-entity generation. To facilitate rigorous evaluation, we construct the first benchmark dataset specifically for DiT-based multi-object motion transfer. MultiMotion demonstrably achieves precise, semantically aligned, and temporally coherent motion transfer for multiple distinct objects, maintaining DiT's high quality and scalability.The code is in the supp.

Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly struggle to maintain spatial-temporal consistency and adapt poorly to rapid temporal variations, due to the lack of effective spatial-temporal modeling. To address these problems, we propose a novel 4D generation network called 4DSTR, which modulates generative 4D Gaussian Splatting with spatial-temporal rectification. Specifically, temporal correlation across generated 4D sequences is designed to rectify deformable scales and rotations and guarantee temporal consistency. Furthermore, an adaptive spatial densification and pruning strategy is proposed to address significant temporal variations by dynamically adding or deleting Gaussian points with the awareness of their pre-frame movements. Extensive experiments demonstrate that our 4DSTR achieves state-of-the-art performance in video-to-4D generation, excelling in reconstruction quality, spatial-temporal consistency, and adaptation to rapid temporal movements.

Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation computational requirements, resulting in generally low generation efficiency. To address this issue, we propose a Hybrid-Grained Cache (HGC) approach that reduces computational overhead by adopting cache strategies with different granularities at different computational stages. Specifically, (1) we use a coarse-grained cache (block-level) based on feature reuse to dynamically bypass redundant computations in encoder-decoder blocks between each step of model reasoning. (2) We design a fine-grained cache (prompt-level) that acts within a module, where the fine-grained cache reuses cross-attention maps within consecutive reasoning steps and extends them to the corresponding module computations of adjacent steps. These caches of different granularities can be seamlessly integrated into each computational link of the controllable generation process. We verify the effectiveness of HGC on four benchmark datasets, especially its advantages in balancing generation efficiency and visual quality. For example, on the COCO-Stuff segmentation benchmark, our HGC significantly reduces the computational cost (MACs) by 63% (from 18.22T → 6.70T↓), while keeping the loss of semantic fidelity (quantized performance degradation) within 1.5%.

Chest X-ray report generation aims to reduce radiologists' workload by automatically producing high-quality preliminary reports. A critical yet underexplored aspect of this task is the effective use of patient-specific prior knowledge---including clinical context (e.g., symptoms, medical history) and the most recent prior image---which radiologists routinely rely on for diagnostic reasoning. Most existing methods generate reports from single images, neglecting this essential prior information and thus failing to capture diagnostic intent or disease progression. To bridge this gap, we propose PriorRG, a novel chest X-ray report generation framework that emulates real-world clinical workflows via a two-stage training pipeline. In Stage 1, we introduce a prior-guided contrastive pre-training scheme that leverages clinical context to guide spatiotemporal feature extraction, allowing the model to align more closely with the intrinsic spatiotemporal semantics in radiology reports. In Stage 2, we present a prior-aware coarse-to-fine decoding for report generation that progressively integrates patient-specific prior knowledge with the vision encoder's hidden states. This decoding allows the model to align with diagnostic focus and track disease progression, thereby enhancing the clinical accuracy and fluency of the generated reports. Extensive experiments on MIMIC-CXR and MIMIC-ABN datasets demonstrate that PriorRG outperforms state-of-the-art methods, achieving a 3.6% BLEU-4 and 3.8% F1 score improvement on MIMIC-CXR, and a 5.9% BLEU-1 gain on MIMIC-ABN.

Commercial-grade poster design demands the seamless integration of aesthetic appeal with precise, informative content delivery. Current automated poster generation systems face significant limitations, including incomplete design workflows, poor text rendering accuracy, and insufficient flexibility for commercial applications. To address these challenges, we propose PosterVerse, a full-workflow, commercial-grade poster generation method that seamlessly automates the entire design process while delivering high-density and scalable text rendering. PosterVerse replicates professional design through three key stages: (1) blueprint creation using fine-tuned LLMs to extract key design elements from user requirements, (2) graphical background generation via customized diffusion models to create visually appealing imagery, and (3) unified layout-text rendering with an MLLM-powered HTML engine to guarantee high text accuracy and flexible customization. In addition, we introduce PosterDNA, a commercial-grade, HTML-based dataset tailored for training and validating poster design models. To the best of our knowledge, PosterDNA is the first Chinese poster generation dataset to introduce HTML typography files, enabling scalable text rendering and fundamentally solving the challenges of rendering small and high-density text. Experimental results demonstrate that PosterVerse consistently produces commercial-grade posters with appealing visuals, accurate text alignment, and customizable layouts, making it a promising solution for automating commercial poster design.

While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video understanding. We introduce ReasonAct, a method that enhances video reasoning in smaller models through a three-stage training process: first building a foundation with text-only reasoning, then fine-tuning on video, and finally refining with temporal-aware reinforcement learning. We build upon Temporal Group Relative Policy Optimization (T-GRPO) by incorporating temporal consistency modeling into policy optimization. We also propose a biomechanically-motivated sub-action decomposition mechanism that provides graduated rewards for constituent action phases. Through experiments on HMDB51, UCF-101, and Kinetics-400, our 3B-parameter model achieves 67.2%, 94.1%, and 78.9% accuracy respectively, demonstrating improvements of 17.9, 15.8, and 12.3 points over baselines. Ablation studies validate that our progressive training enables smaller models to achieve competitive video reasoning performance while maintaining computational efficiency.

Real-time stereo matching methods primarily focus on enhancing in-domain performance but often overlook the critical importance of generalization in real-world applications. In contrast, recent stereo foundation models leverage monocular foundation models (MFMs) to improve generalization, but typically suffer from substantial inference latency. To address this trade-off, we propose Generalized Geometry Encoding Volume (GGEV), a novel real-time stereo matching network that achieves strong generalization. We first extract depth-aware features that encode domain-invariant structural priors as guidance for cost aggregation. Subsequently, we introduce a Depth-aware Dynamic Cost Aggregation (DDCA) module that adaptively incorporates these priors into each disparity hypothesis, effectively enhancing fragile matching relationships in unseen scenes. Both steps are lightweight and complementary, leading to the construction of a generalized geometry encoding volume with strong generalization capability. Experimental results demonstrate that our GGEV surpasses all existing real-time methods in zero-shot generalization capability, and achieves state-of-the-art performance on the KITTI 2012, KITTI 2015, and ETH3D benchmarks.

The emergence of large vision-language models (VLMs) has significantly enhanced the efficiency and flexibility of geospatial interpretation. However, general-purpose VLMs remain suboptimal for remote sensing (RS) tasks. Existing geospatial VLMs typically adopt a unified modeling strategy and struggle to differentiate between task types and interpretation granularities, limiting their ability to balance local detail perception and global contextual understanding. In this paper, we present SkyMoE, a Mixture-of-Experts (MoE) vision-language model tailored for multimodal, multi-task RS interpretation. SkyMoE employs an adaptive router that generates task- and granularity-aware routing instructions, enabling specialized large language model experts to handle diverse sub-tasks. To further promote expert decoupling and granularity sensitivity, we introduce a context-disentangled augmentation strategy that creates contrastive pairs between local and global features, guiding experts toward level-specific representation learning. We also construct MGRS-Bench, a comprehensive benchmark covering multiple RS interpretation tasks and granularity levels, to evaluate generalization in complex scenarios. Extensive experiments on 21 public datasets demonstrate that SkyMoE achieves state-of-the-art performance across tasks, validating its adaptability, scalability, and superior multi-granularity understanding in remote sensing.