IJCAI 2026 论文列表

Sea surface variable reconstruction from sparse observations is a key ocean-science challenge. Traditional methods, such as the four-dimensional variational (4DVar) approach, rely on numerical models for background information, leading to high computational costs. Deep learning methods are more efficient but often fail to capture eddy dynamics, resulting in limited effective resolution. We propose 4DVarGen, a 4DVar-inspired generative framework for reconstructing sea surface variable fields at eddy-resolving scales from sparse remote-sensing observations. 4DVarGen establishes a mathematical equivalence between 4DVar and an observation-guided denoising process. Its key innovation is injecting the observation-likelihood gradient into denoising iterations, driving the generated trajectories to evolve in the direction of minimizing the 4DVar objective function toward a maximum a posteriori solution. Spatiotemporal priors learned by a diffusion model serve as background information, reducing computational costs and mitigating the adverse effects of Gaussian assumptions. Experiments show that 4DVarGen effectively leverages the temporal evolution patterns of sea surface temperature (SST) and sea surface height (SSH), as well as their dynamical mappings learned by the diffusion model, leading to improved reconstruction accuracy and effective resolution. Our model, pretrained on GLORYS12V1 reanalysis data, generates sea surface variable fields guided by real observations, achieving accuracy and effective resolution improvements of 18% and 58%, respectively, compared to GLORYS12V1. This study offers a novel framework for reconstructing Earth system states from sparse observations.

Hand Object Interaction (HOI) generation provides an efficient solution for virtual reality simulation and embodied AI deployment.Recent studies have explored instruction-driven HOI synthesis, yet they overlooked the fine-grained interactive contact and struggled with robust generalization in data-scarce scenarios. In addition, existing datasets are frequently constrained with limited object categories and monotonous motion patterns. To address these limitations, we first integrate a large-scale HOI dataset, namely HOI-X, which contains diverse objects, rich motion patterns, and part-level contact annotations. Along with HOI-X, we propose A3fford-HOI, a fine-grained and generalizable Hand Object Interaction framework with Anatomy-Aligned Affordance Disentanglement. Specifically, we define a Disentangle-2-Interact paradigm in A3fford-HOI. Considering the various interactions of distinct hand anatomical structures, in the Disentangle stage, we devise an Anatomy-Aligned Affordance Predictor, which leverages the external plausible physical priors in 3D multimodal large language models for affordance disentanglement prediction. Then, the disentangled affordance is employed into the Interact stage, i.e. Affordance Driven Interactor. The interactor integrates textual instructions, object geometric features, and the external knowledge enhanced (MLLMs) affordance via a Diffusion Transformer (DiT) for generalizable HOI generation. Extensive experiments demonstrate that A3fford-HOI maintains superior generation quality and contact plausibility for fine-grained and generalizable hand object interaction.

Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments with articulated robots and manipulable objects remains difficult due to complex contact interactions and abrupt pose changes. To address these challenges, we introduce ManiSplat, a unified framework that reconstructs controllable and decoupled Gaussian digital twins directly from monocular ego-view robotic videos. Our method introduces a Graph-Structured Disentangled Representation that separates the robot, objects, and background into independently optimizable Gaussian subfields organized within a scene graph. To ensure stability, we propose a Task-Oriented Spatio-Temporal Alignment module that leverages the inherent logic of manipulation tasks—alternating between Motion and Skill phases—to construct accurate pseudo-ground-truth trajectories. Finally, a joint photometric-geometric optimization ensures the reconstructed scenes are temporally coherent, physically consistent, and simulation-ready. Extensive experiments demonstrate that our approach reconstructs interaction-driven dynamic scenes with high fidelity and controllability, effectively supporting downstream robotic tasks and policy learning.

Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision--language tasks. However, their capabilities remain unclear in relational-diagram (RD) reasoning, where correct answers must satisfy diagram-defined constraints such as directed dependencies, branching conditions, and prerequisite relations. RDs, including hierarchical diagrams, fishbone diagrams, and flowcharts, require models to not only retrieve nodes and relations, but also maintain valid reasoning paths over multi-step dependency chains. In this paper, we introduce RD-Bench, a large-scale benchmark of verified diagram--question pairs covering three diagram categories and four difficulty levels. RD-Bench evaluates hierarchical localization, branch-condition selection, constraint-guided traversal, step counting, and prerequisite identification. Experiments on representative open-source and proprietary MLLMs reveal a consistent limitation: models perform much better on single-step reasoning than on multi-step dependency reasoning, especially for complex flowcharts with branching logic and long-range prerequisites. To reduce this gap, we propose RD-MCTS, a Monte Carlo Tree Search framework that incorporates diagram-derived structural priors, constraint-consistent state transitions, and inference-time step-level process rewards. RD-MCTS guides search toward dependency-relevant nodes and valid next steps, improving constraint-consistent reasoning on high-difficulty questions.

Generative models continue to advance rapidly in both fidelity and diversity, posing increasing challenges for reliably distinguishing generated images from real ones. Existing reconstruction-based detection methods often rely on assumptions tied to specific generative models, which leads to limited cross-model generalization and substantial computational overhead. In this paper, we propose General Feature Reconstruction Error (GFRE), a fast and generalizable detection paradigm that leverages reconstruction behavior in a general-purpose representation space. Our key insight is that real and generated images exhibit consistently different reconstruction stability when projected into universal visual representations. Instead of tracing generator-specific artifacts, GFRE employs a lightweight autoencoder to model the reconstructability of image representations, producing a reconstruction signal that is inherently generator-agnostic and transferable across diverse generative processes. Extensive experiments on images synthesized by 18 different generative models demonstrate that GFRE consistently outperforms existing state-of-the-art methods, achieving a 4.70% improvement in detection accuracy and an 8.20% gain in cross-model generalization. Moreover, by avoiding costly generator inversion and diffusion-based reconstruction, GFRE reduces reconstruction error extraction time by up to 150x, enabling efficient and scalable deployment.

Recent works in Gaussian Splatting (GS) SLAM highlight the importance of geometric structure. However, existing methods often rely on either 2D or 3D Gaussian primitives, lacking the balance between geometry and appearance, thus failing to precisely model spatial structures. Furthermore, current frameworks either solely utilize SLAM to provide poses for GS or optimize poses and all Gaussian parameters indiscriminately, which neglect geometric consistency constraints essential for robust localization, creating a gap between GS and SLAM. In this paper, a tight-coupling SLAM system based on a Geometric Gaussian Field (GGF) is proposed. First, GGF combines explicit spatial structures with implicit neural residuals to adaptively regulate the Gaussian morphologies, seamlessly transitioning between 2D and 3D Gaussian primitives, ensuring precise spatial modeling. Second, a Geometric Consistency-Guided Refinement (GCGR) strategy is introduced, which exploits depth and normal maps rendered by GGF to construct critical constraints for accurate pose estimation. Simultaneously, updated poses and spatial information are fed back to refine Gaussian morphology, establishing mutual enhancement and tight-coupling between GS and SLAM. Extensive experiments demonstrate that GGF-SLAM outperforms state-of-the-art methods in tracking accuracy, photorealistic rendering, and geometric reconstruction.

Dynamic 3D reconstruction of surgical scenes plays a critical role in robotic-assisted surgery. Gaussian Splatting (GS), while effective for novel view synthesis, struggles to recover accurate surface from a monocular view due to the implicit multi-Gaussian representation of the surface. Specifically, (1) the vertical overlap of Gaussians leads to floating artifacts, and (2) the random orientation of Gaussians affects the smoothness of the reconstructed surface. Consequently, these fragmented and misaligned Gaussians hinder downstream applications, e.g., geometry-aware endoscopic navigation and physics-integrated tissue mechanics simulation. To this end, we propose Endo-GSG, a unified framework that couples dynamic Gaussian splatting with an SDF field for dynamic surface-aware tissue reconstruction. To further enhance geometric fidelity, we design geometry-informed regularization losses that constrain Gaussian density and spatial positioning. The entire pipeline is jointly supervised by RGB images and predicted depth maps, enabling high-quality reconstruction and rendering even with sparse or monocular input. Experiments on public datasets demonstrate that Endo-GSG outperforms state-of-the-art methods in both rendering quality and geometric surface accuracy.

Effective multimodal learning in real-world scenarios depends on a nuanced treatment of uncertainty, which arises at three levels: (1) Intrinsic Uncertainty from modality-specific noise or ambiguity; (2) Relational Uncertainty due to cross-modal conflicts or redundancy; and (3) Aggregated Uncertainty when fusing potentially inconsistent signals. Most existing methods overlook this hierarchy, applying a single uncertainty model. We propose Adaptive Evidential Multimodal Representation Learning (AEMRL), a framework aligned with this multi-level view. To address intrinsic uncertainty, Disentangled Evidential Uncertainty Encoding (D-EUE) provides interpretable, class-aware reliability scores per modality. For relational uncertainty, Uncertainty-Conditioned Dynamic Factorization (UDF) uses a hypernetwork to dynamically extract complementary cues and suppress conflict. To resolve aggregated uncertainty, Adaptive Fusion & Conflict-Aware Calibration (AFCAC) adaptively weights evidence streams and calibrates final predictions based on detected conflicts. Extensive experiments on five diverse benchmark datasets show that AEMRL consistently enhances task accuracy, reduces calibration error, and improves robustness to noise, semantic conflict, and missing modalities.

Unified segmentation aims to consolidate multiple vision tasks into a single model, yet faces two core challenges: learning robust homogeneous features (e.g., shared low- and mid-level cues) to enable cross-domain knowledge transfer, while disentangling heterogeneous features (e.g., task-specific semantic objectives) to avoid negative transfer and preserve task independence. To address these challenges, we propose the Homo- and Heterogeneous Network (H2Net), a unified framework that jointly models shared homogeneous representations and task-specific heterogeneous features. Specifically, H2Net incorporates a Cross-Modal Structure Enhancement Module (CSEM), which integrates auxiliary depth priors via joint frequency–spatial cross-modal attention to strengthen task-agnostic structural representations. In addition, a Task Adapter Pool (TAP) is introduced to model task-specific heterogeneous features by assigning dedicated adapters to individual tasks, enabling task-aware feature modulation and semantic disentanglement within a shared backbone. Extensive experiments on benchmarks spanning eight tasks demonstrate the effectiveness of the proposed approach and its superior performance. Code and results will be available at https://h2net-ijcai26.github.io.

Achieving visual coordination between egocentric (ego) and exocentric (exo) perspectives is a cornerstone of augmented reality and human-machine collaboration. However, extreme viewpoint shifts and occlusions often cause semantic drift in existing methods, making robust cross-view correspondence a formidable challenge. In this paper, we propose SARA (Semantic-Anchored Referential Alignment), a framework designed to bridge the ego-exo gap by leveraging viewpoint-invariant, high-level semantic information as region-level semantic anchors for robust feature mapping. Specifically, our approach incorporates: (1) the Semantic Anchoring Module extracts cross-view category priors and invariant features to provide stable region-level references across perspectives, and (2) the Multimodal Semantic Vector Fusion mechanism achieves language-guided manifold fusion of semantic vectors to synthesize unified embeddings, effectively establishing representational correspondence across disparate perspectives. Extensive experiments across diverse, complex scenarios demonstrate SARA’s superior performance in establishing stable mappings,validating the effectiveness of semantic-invariant features and multimodal fusion in addressing the core hurdles of cross-view understanding.

Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally "thin" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide. We present MELLA, a multimodal dataset across eight low-resource languages, designed to jointly support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture-grounded supervision with generated-and-translated image descriptions for linguistically rich supervision, explicitly separating two learning signals often conflated in multilingual multimodal data. Through controlled diagnostic fine-tuning on multiple MLLM backbones, we show that MELLA mitigates cultural hallucination by helping models recognize and articulate culturally specific entities overlooked by translation-based adaptation. Our findings highlight data alignment, rather than model modification alone, as a key path toward culturally grounded multimodal understanding in low-resource languages.

Acquiring three-dimensional(3D) microstructural images of cement hydration reveals critical microscale features essential for understanding hydration mechanisms and advancing material development. Micro-computed tomography(µCT) is widely used to capture these images due to its non-destructive, repeatable 3D imaging capability, despite at high operational cost. However, µCT suffers from limited resolution, weak texture, and missing phase information. In contrast, backscattered electron(BSE) provides high-resolution, phase-sensitive, and texture-rich images but are confined to 2D form. Inspired by the idea of fusing BSE style into µCT images for computationally imaging 3D BSE data, this paper proposes a cross-device generation method, termed CT2BSE, to construct 3D BSE microstructural images from µCT for cement hydration. A Voxel Swin Transformer is proposed to extract 3D μCT features by improving Video Swin Transformer with a Content-Aware Positional Encoding–3D, making encoder better suited for homogeneous images such as cement. Furthermore, a Holistic Style Injector–3D is proposed to fuse 3D μCT features with 2D BSE characteristics, thereby mitigating feature instability caused by the extreme intensity variations typically exhibited in cement images. Subsequently, the fused features are decoded into 3D volumes aligned with the BSE style while preserving original microstructure. Experimental results demonstrate that CT2BSE can generate high-fidelity 3D BSE images from μCT.

Recently, Visual State Space Models offer powerful global modeling for Dual-modal Salient Object Detection (SOD). However, they are still constrained by three inherent limitations: first, Mamba's strict reliance on sequential ordering makes it sensitive to cross-modal geometric misalignment, where spatial shifts disrupt token correspondence; second, general indiscriminate scanning treating all tokens equally may lead to signal dilution, where sparse foreground features are overwhelmed by background noise; third, conventional decoders rely on implicit upsampling, causing boundary degradation during resolution recovery. To address these challenges, we propose G-SalAlignMamba, a geometry-aware framework tailored for dual-modal SOD. We introduce Geometry-Aware Encoding with explicit alignment to correct spatial shifts, Semantics-Informed Refinement to prevent signal dilution by prioritizing foregrounds, and Structure-Preserving Decoding that integrates explicit alignment with unsupervised boundary refinement. Extensive experiments show that G-SalAlignMamba achieves state-of-the-art performance on RGB-D and RGB-T benchmarks with favorable efficiency (30.41 FPS, 83.80M parameters). The code is available at https://github.com/PC1-99/G-SalAlignMamb.git.

We present D3Adapter, a threat-aware framework that unifies adversarial example detection (AED) and robust inference. D3Adapter attaches a small library of lightweight adapters to a frozen ResNet backbone; the adapters are trained under two loss functions (cross-entropy and optimized reverse cross-entropy) and complementary objectives (clean training and adversarial training), yielding intentionally distinct logit behaviors. During inference, D3Adapter quantifies inter-adapter logit divergence to produce an agreement-based threat score without any external detector for AED. The same pass also performs robust inference by outputting prediction from the selected adapter when an adversarial example is detected, therefore unifying detection and defense into single-pass forward computation. We evaluate D3Adapter under transfer-based and adaptive white-box attacks, and we study scalability across datasets with varying numbers of classes, showing that unified detection and robust inference can be achieved with predictable overhead proportional to the number of adapters.

Vision-based trajectory prediction with BEV representations has achieved promising results, yet existing methods often suffer from limited temporal modeling and insufficient characterization of motion dynamics. To address these issues, we propose a temporally enhanced framework with explicit motion parameter prediction. Specifically, we introduce BEVFormer++, which leverages multi-view images and BEV features from multiple preceding timesteps to generate more robust BEV representations, along with BEV differential features to capture temporal variations. Moreover, we propose a motion-parameter-decoupled tracking module that explicitly estimates velocity, acceleration, and heading angle, providing informative motion cues for trajectory prediction. Extensive experimental results demonstrate that our method outperforms state-of-the-art approaches and can be seamlessly integrated into existing vision-based frameworks, consistently yielding performance improvements.

3D Gaussian Splatting enables efficient, high-fidelity novel view synthesis with explicit Gaussians and differentiable rendering. However, adverse weather introduces rain streaks and droplets as well as volumetric scattering, producing view-dependent, spatially varying degradations that break the clean multi-view consistency assumption and lead to geometric drift and unstable appearance. Existing approaches are largely confined to the 2D image domain and seldom model the 3D degradation formation process, limiting controllable weather synthesis and consistent restoration in 3DGS. To our knowledge, we are the first to incorporate real meteorological observations as an external prior and propose a 3D-level unified rendering–restoration framework for joint deraining and dehazing within a single 3DGS pipeline. Precipitation is mapped to interpretable parameters controlling the density and morphology of rain Gaussians, while an atmospheric-scattering extinction strength drives 3D fog generation for reproducible weather modeling. We adopt a closed-loop dual-branch optimization where the rendering branch fits degraded observations to capture weather degradation patterns, and the restoration branch regularizes scene Gaussians toward a clean domain with multi-scale perceptual consistency, suppressing artifacts and improving cross-view detail fidelity. Experiments across diverse scenes and weather conditions consistently outperform strong baselines on all three metrics, with a particularly notable PSNR improvement of 1.78 dB on average.

High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While diffusion models provide strong generative priors for this task, their inference cost grows prohibitively with resolution. We propose HRSino, a training-free and efficient diffusion inference approach for high-resolution sinogram completion. By explicitly accounting for spatial heterogeneity in signal characteristics, such as spectral sparsity and local complexity, HRSino allocates inference effort adaptively across spatial regions and resolutions, rather than applying uniform high-resolution diffusion steps. This enables global consistency to be captured at coarse scales while refining local details only where necessary. Experimental results show that HRSino reduces peak memory usage by up to 30.81% and inference time by up to 17.58% compared to the state-of-the-art framework, and maintains completion accuracy across datasets and resolutions.

Accurate identification of non-rigid motion is crucial for geometric validity in self-supervised monocular depth estimation (MDE), yet it remains challenging for current methods. Inspired by Human Visual Perception (HVP), we present VFM-Dynamo, an efficient self-supervised MDE framework that disambiguates non-rigid objects by combining a vision foundation model (VFM) such as Grounding DINO and SAM with coarse to fine motion identification strategy: 1) Integrating visual-textual feature dependencies, we activate the capability of Grounding DINO global understanding with text prompts to detect potential object bounding boxes. 2) We then estimate coarse motion mask from reprojection error and photometric consistency to separate static from dynamic content. This mask provides coarse guidance for constraining rigid flow in static regions through two analogous estimates aligned by a consistency loss, and it drives a non-dynamical suppression module that removes boxes associated with static objects. 3) The remaining boxes are used to prompt SAM to produce refined motion identification, which in turn guide the joint optimization of depth and optical flow. Additionally, due to foreground–background mixing, standard interpolation-based upsampling often produces boundary artifacts. We introduce a learnable neighbor affinity interpolation (LNAI) module, which directly upsamples depth to full resolution and can be seamlessly integrated as a plug-and-play component. Experiments on a series of benchmarks demonstrate that proposed framework achieves state-of-the-art performance among unsupervised methods. Code is available at https://github.com/Qianqian3764/VFM-Dynamo.

Monocular 3D object detection is a cost-efficient alternative to multisensor systems, yet it remains fragile to multi-component adversarial attacks that perturb the image and tamper with camera calibration. Compounded distortions degrade 3D reasoning by disrupting the correspondence between the 3D geometry and 2D image plane. To address this problem, this work proposes MonoPure, a monocular 3D object detection framework that performs multi-component purification via disentangled and projective representations. MonoPure incorporates a disentangled purification and segmentation module that purifies the image data, with a target-region probability map steering diffusion-based purification to focus on task-relevant regions. In addition, MonoPure presents a 3D detection decoder that integrates 2D skeleton keypoints as object-level spatial cues, enabling occlusion-robust 3D detection. Finally, a projective calib-purification module restores compromised intrinsics by iteratively minimizing the reprojection error between projected 3D boxes and calibration-invariant 2D detection boxes. The experiments confirm that MonoPure outperforms prior detectors under multi-component attacks and occlusion.