AAAI 2026 论文列表

Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D SLAM system that leverages a hierarchically constrained neural Gaussian representation to preserve structural relationships while generating Gaussian primitives for scene mapping. It also employs progressive pose optimization to mitigate depth sensor noise, significantly enhancing localization accuracy. Furthermore, it utilizes a dynamic neural representation graph that adjusts the distribution of Gaussian nodes based on local geometric complexity, enabling the map to adapt to intricate scene details in real time. This combination yields high-precision 3D mapping and photorealistic scene rendering. Experimental results show PointSLAM++ outperforms existing 3DGS-based SLAM methods in reconstruction accuracy and rendering quality, demonstrating its advantages for large-scale AR and robotics.

Text-driven human motion generation has recently attracted considerable attention, allowing models to generate human motions based on textual descriptions. However, current methods neglect the influence of human attributes—such as age, gender, weight, and height—which are key factors shaping human motion patterns. This work represents a pilot exploration for bridging this gap. We conceptualize each motion as comprising both attribute information and action semantics, where textual descriptions align exclusively with action semantics. To achieve this, a new framework inspired by Structural Causal Models is proposed to decouple action semantics from human attributes, enabling text-to-semantics prediction and attribute-controlled generation. The resulting model is capable of generating attribute-aware motion aligned with the user's text and attribute inputs. For evaluation, we introduce a comprehensive dataset containing attribute annotations for text-motion pairs, setting the first benchmark for attribute-aware motion generation. Extensive experiments validate our model's effectiveness.

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth

At present, most hyperspectral (HS) sharpening methods have not fully utilized the feature correlation between adjacent bands in HS images, nor have they explored the problem of feature uncertainty generated by the model during the fusion process. This may lead to inaccurate fusion features generated by the model, resulting in spatial and spectral distortions in the fusion results. To address these issues, we propose an uncertainty-guided memory network (UMNet) for HS pansharpening. A spatial-spectral recurrent fusion unit (SRFU) is designed based on the concept of temporal data modeling, which utilizes the correlation between adjacent bands to fuse spectral and spatial features from PAN and LRHS images. In SRFU, a state memory interaction unit (SMIU) is constructed based on non-negative matrix factorization (NMF) to learn the global spatial-spectral dependency of PAN and HS images in the recurrent state space. Moreover, based on uncertainty theory, we define two spatial-spectral uncertainty-guided loss functions for the HS pansharpening task to train the model step by step, ensuring that the network can reconstruct more accurate spectral and spatial features. Extensive experiments on three widely used datasets demonstrate that, compared with some state-of-the-art (SOTA) methods, the proposed UMNet has achieved significant improvements in both spatial and spectral quality metrics.

Deep Unrolling Networks (DUNs) integrate classical optimization recovery problems in Compressed Sensing (CS) with sophisticated deep learning network architectures, leading to substantial breakthroughs. However, prevailing DUNs generally face challenges concerning solidified gradient descent step size strategies, inadequate feature extraction within the iterative stage and limited information interaction between iterative stages. To overcome these obstacles, we propose SCU-Net, a channel-focused unrolling network inspired by the renowned spectral projected gradient optimization algorithm. In particular, we tailore two pivotal components, Barzilai-Borwein-gradient Descent Optimizer (BBDO) and Channel-guided Cross-attention Reconstruction Module (CCRM), to collaboratively undertake the reconstruction task. BBDO leverages a gradient calculation strategy based on BB step size to enhance data fidelity optimization, while CCRM addresses the intricate mapping issue associated with sparse induction, encompassing customized functionalities from Adaptive Channel Interaction Layer (ACIL) and Spatially Augmented Channel-aware Unit (SACU). Among them, ACIL amalgamates convolution operations and channel attention mechanisms to achieve meticulous information screening alongside efficient feature enhancement. SACU introduces dual reinforcement variables to bolster information exchange across different iterative stages, coupled with the optimization of cross-attention to facilitate the modeling of long-distance dependencies. Extensive experiments in both image CS and magnetic resonance imaging exhibit that our SCU-Net manifests superior performance, surpassing state-of-the-art methods.

Infrared unmanned aerial vehicle (UAV) target images often suffer from motion blur degradation caused by rapid sensor movement, significantly reducing contrast between target and background. Generally, detection performance heavily depends on the discriminative feature representation between target and background. Existing methods typically treat deblurring as a preprocessing step focused on visual quality, while neglecting the enhancement of task-relevant features crucial for detection. Improving feature representation for detection under blur conditions remains challenging. In this paper, we propose a novel Joint Feature-Domain Deblurring and Detection end-to-end framework, dubbed JFD³. We design a dual-branch architecture with shared weights, where the clear branch guides the blurred branch to enhance discriminative feature representation. Specifically, we first introduce a lightweight feature restoration network, where features from the clear branch serve as feature-level supervision to guide the blurred branch, thereby enhancing its distinctive capability for detection. We then propose a frequency structure guidance module that refines the structure prior from the restoration network and integrates it into shallow detection layers to enrich target structural information. Finally, a feature consistency self-supervised loss is imposed between the dual-branch detection backbones, driving the blurred branch to approximate the feature representations of the clear one. We also construct a benchmark, named IRBlurUAV, containing 30,000 simulated and 4,118 real infrared UAV target images with diverse motion blur. Extensive experiments on IRBlurUAV demonstrate that JFD³ achieves superior detection performance while maintaining real-time efficiency.

Recent researchers have proposed using event cameras for person re-identification (ReID) due to their promising performance and better balance in terms of privacy protection, event camera-based person ReID has attracted significant attention. Currently, mainstream event-based person ReID algorithms primarily focus on fusing visible light and event stream, as well as preserving privacy. Although significant progress has been made, these methods are typically trained and evaluated on small-scale or simulated event camera datasets, making it difficult to assess their real identification performance and generalization ability. To address the issue of data scarcity, this paper introduces a large-scale RGB-event based person ReID dataset, called EvReID. The dataset contains 118,988 image pairs and covers 1200 pedestrian identities, with data collected across multiple seasons, scenes, and lighting conditions. We also evaluate 15 state-of-the-art person ReID algorithms, laying a solid foundation for future research in terms of both data and benchmarking. Based on our newly constructed dataset, this paper further proposes a pedestrian attribute-guided contrastive learning framework to enhance feature learning for person re-identification, termed TriPro-ReID. This framework not only effectively explores the visual features from both RGB frames and event streams, but also fully utilizes pedestrian attributes as mid-level semantic features. Extensive experiments on the EvReID dataset and MARS datasets fully validated the effectiveness of our proposed RGB-Event person ReID framework.

Cross-modal retrieval is crucial for discovering latent correspondences across different modalities. However, existing methods typically assume that training data are well-aligned, an unrealistic assumption since real-world datasets inevitably contain noisy correspondences. Many current approaches attempt to handle noise using strategies borrowed from single-modal classification, such as the small-loss trick, to identify clean training pairs. However, our experiments reveal that such small-loss-based strategies are less effective for multi-modal tasks due to the inherent modality gaps. Through comprehensive analysis, we observe that the deviation directions between paired image-caption features, termed Sample-level Alignment Drift (SAD), are compact and data-dependent. Leveraging this discovery, we introduce the Modality Gap Corrected Similarity (MGCS) framework that can more accurately measure the semantic distances of cross-modal samples, dynamically compensating for misalignments. Within MGCS, we can achieve more reliable noisy data separation to promote correct supervision during cross-modal matching model training. Extensive experiments on three widely used noisy correspondence benchmarks demonstrate that MGCS significantly surpasses current state-of-the-art methods.

The growing exploration of Large Language Models (LLM) and Vision-Language Models (VLM) has opened avenues for enhancing the effectiveness of reinforcement learning (RL). However, existing LLM-based RL methods often focus on the guidance of control policy and encounter the challenge of limited representations of the backbone networks. To tackle this problem, we introduce Enhanced Semantic Motion Representations (Semore), a new VLM-based framework for visual RL, which can simultaneously extract semantic and motion representations through a dual-path backbone from the RGB flows. Semore utilizes VLM with common-sense knowledge to retrieve key information from observations, while using the pre-trained clip to achieve the text-image alignment, thereby embedding the ground-truth representations into the backbone. To efficiently fuse semantic and motion representations for decision-making, our method adopts a separately supervised approach to simultaneously guide the extraction of semantics and motion, while allowing them to interact spontaneously. Extensive experiments demonstrate that, under the guidance of VLM at the feature level, our method exhibits efficient and adaptive ability compared to state-of-the-art methods. All codes are released.

Image-based feature representation plays a critical role in visual localization, enabling robots to estimate their position and orientation in GPS-denied environments. However, this task is often undermined by significant variations in camera viewpoints and scene appearances. Recently, map-free visual relocalization (MFVR) has emerged as a promising paradigm due to its compatibility with lightweight deployment and privacy isolation on mobile devices. In this paper, we propose the Debiased Multiplex Tokenizer (DeMT) as a novel method for versatile and efficient MFVR. Specifically, DeMT performs relative pose regression through an integrated framework built upon a pretrained vision Mamba encoder, comprising three key modules: First, Multiplex Interactive Tokenization yields robust image tokens with non-local affinities and cross-domain descriptions; Second, Debiased Anchor Registration facilitates anchor token matching through proximity graph retrieval and causal pointer attribution; Third, Geometry-Informed Pose Regression empowers multi-layer perceptrons with a gating mechanism and spectral normalization to support both pair-wise and multi-view modes. Extensive evaluations across nine public datasets demonstrate that DeMT substantially outperforms existing baselines and ablation variants in diverse indoor and outdoor environments.

Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving. While most existing approaches follow an ego-centric paradigm by aggregating and diffusing features over the entire scene, they often overlook fine-grained object-level details, leading to semantic and geometric ambiguities, especially in complex environments. To address this limitation, we propose Ocean, an object-centric prediction framework that decomposes the scene into individual object instances to enable more accurate semantic occupancy prediction. Specifically, we first employ a lightweight segmentation model, MobileSAM, to extract instance masks from the input image. Then, we introduce a 3D Semantic Group Attention module that leverages linear attention to aggregate object-centric features in 3D space. To handle segmentation errors and missing instances, we further design a Global Similarity-Guided Attention module that leverages segmentation features for global interaction. Finally, we propose an Instance-aware Local Diffusion module that improves instance features through a generative process and subsequently refines the scene representation in the BEV space. Extensive experiments on the SemanticKITTI and SSCBench-KITTI360 benchmarks demonstrate that Ocean achieves state-of-the-art performance, with mIoU scores of 17.40 and 20.28, respectively.

We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for objects or faces typically require a high-resolution RGB image as input. When dealing with degraded images, the conventional pipeline follows a two-stage process: first restoring the image to high resolution, then synthesizing novel views from the restored result. However, this approach is highly dependent on the quality of the restored image, often leading to inaccuracies and inconsistencies in the final output. To address this limitation, we extract single-view features directly from the blind face image and introduce a feature manipulator that transforms these features into 3D-aware, multi-view latent representations. Leveraging the powerful generative capacity of a diffusion model, our framework synthesizes high-quality, consistent novel-view face images. Experimental results show that our method significantly outperforms traditional two-stage approaches in both consistency and fidelity.

Although geometric reconstruction of general objects from images has made remarkable progress in recent years, slender structures remain largely underexplored, despite their critical importance in engineering, biomedical, and agricultural applications. To bridge this gap, we propose a dedicated 2DGS-based geometric reconstruction framework tailored for slender structures, achieving accurate and faithful geometry recovery. Our method first addresses the challenge that most slender objects are texture-less, which hinders reliable feature matching and pose estimation in traditional SfM pipelines. By leveraging the curve-like nature of slender structures, we perform a curve-guided SfM process that provides robust camera poses and accurate 3D curve initialization for Gaussian primitives. To ensure SfM reliability, we introduce a high-precision mask extraction strategy that integrates geometric priors with a segmentation network, effectively handling self-occlusion and thin geometry. Furthermore, to enhance fine geometric recovery, we incorporate a differentiable Poisson reconstruction module to extract an initial mesh during training, which is then refined via image-space iterative optimization using differentiable mesh rasterization. In contrast to conventional approaches that rely on differentiable Gaussian rasterization followed by TSDF-based mesh extraction, our method avoids the additional geometric errors and artifacts introduced during the intermediate TSDF conversion, thereby improving the overall reconstruction quality. Comprehensive experiments on both synthetic and real-world datasets validate that our method achieves superior reconstruction quality compared to state-of-the-art approaches.

Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too memory-intensive for direct input into conventional diffusion models. Furthermore, general generative models lack an understanding of the topological and geometric structures of ground objects in remote sensing imagery. In addition, most diffusion models optimize loss functions at the noise level, leading to a non-intuitive convergence behavior and suboptimal generation quality for complex data. To address these challenges, we propose a Geometric Enhanced Wavelet-based Diffusion Model (GEWDiff), a novel framework for reconstructing hyperspectral images at 4-times super-resolution. A wavelet-based encoder-decoder is introduced that efficiently compresses HSIs into a latent space while preserving spectral-spatial information. To avoid distortion during generation, we incorporate a geometry-enhanced diffusion process that preserves the geometric features. Furthermore, a multi-level loss function was designed to guide the diffusion process, promoting stable convergence and improved reconstruction fidelity. Our model demonstrated state-of-the-art results across multiple dimensions, including fidelity, spectral accuracy, visual realism, and clarity.

Accurate prediction of driving intention is key to enhancing the safety and interactive efficiency of human-machine co-driving systems. It serves as a cornerstone for achieving high-level autonomous driving. However, current approaches remain inadequate for accurately modeling the complex spatiotemporal interdependencies and the unpredictable variability of human driving behavior. To address these challenges, we propose CaTFormer, a causal Temporal Transformer that explicitly models causal interactions between driver behavior and environmental context for robust intention prediction. Specifically, CaTFormer introduces a novel Reciprocal Delayed Fusion (RDF) mechanism for precise temporal alignment of interior and exterior feature streams, a Counterfactual Residual Encoding (CRE) module that systematically eliminates spurious correlations to reveal authentic causal dependencies, and an innovative Feature Synthesis Network (FSN) that adaptively synthesizes these purified representations into coherent temporal representations. Experimental results demonstrate that CaTFormer attains state-of-the-art performance on the Brain4Cars dataset. It effectively captures complex causal temporal dependencies and enhances both the accuracy and transparency of driving intention prediction.

Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remarkable capabilities. However, their practical deployment is often hindered by slow inference speeds and high memory consumption. In this paper, we propose a novel pipelining framework named PipeDiT to accelerate video generation, which is equipped with three main innovations. First, we design a pipelining algorithm (PipeSP) for sequence parallelism (SP) to enable the computation of latent generation and communication among multiple GPUs to be pipelined, thus reducing the inference latency. Second, we propose DeDiVAE to decouple the diffusion module and the VAE module into two GPU groups whose executions can also be pipelined to reduce the memory consumption and inference latency. Third, to better utilize the GPU resources in the VAE group, we propose an attention co-processing (Aco) method to further reduce the overall video generation latency. We integrate our PipeDiT into both OpenSoraPlan and HunyuanVideo, two state-of-the-art open-source video generation frameworks, and conduct extensive experiments on two 8-GPU systems. Experimental results show that, under many common resolution and timestep configurations, our PipeDiT achieves 1.06× to 4.02× speedups over OpenSoraPlan and HunyuanVideo.

Mainstream multimodal large language models (MLLMs) rely on patch-based tokenization methods, which compromise the integrity of objects and thereby limit the model's perception capabilities while triggering object-related hallucinations. To address this issue, we propose ObjecTok, an innovative object tokenization framework. ObjecTok generates a single, holistic object token for each object in an image. This token is produced by a specially trained object encoder that embeds the object's semantic, positional, and shape information into a single compact representation, thereby preserving the object's integrity. To mitigate the imperfections of upstream object proposer models, we introduce learnable confidence embeddings. These embeddings enable the MLLM to learn the reliability of each object's information, significantly enhancing the model's robustness. Additionally, ObjecTok employs a hybrid input strategy, combining object tokens with traditional image patch tokens, allowing the model to leverage both object-level information and global scene context. By integrating ObjecTok into the LLaVA architecture, we achieve notable performance improvements on multiple object-centric benchmarks, effectively reducing object hallucinations and enhancing perception capabilities. Experimental results robustly demonstrate that the object tokens generated by our ObjecTok framework hold great potential for building more powerful and reliable MLLMs.

Vision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents.

Most existing multi-modal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative temporal representations. To address these limitations, we propose MDTrack, a novel framework for modality-aware fusion and decoupled temporal propagation in multi-modal object tracking. Specifically, for modality-aware fusion, we allocate dedicated experts to each modality (Infrared, Event, Depth, and RGB) to process their respective representations. The gating mechanism within the Mixture of Experts (MoE) then dynamically selects the optimal experts based on the input features, enabling adaptive and modality-specific fusion. For decoupled temporal propagation, we introduce two separate State Space Model (SSM) structures to independently store and update the hidden states h of the RGB and X-modal streams, effectively capturing their distinct temporal information. To ensure synergy between the two temporal representations, we incorporate a set of cross-attentions between the input features of the two SSMs, facilitating implicit information exchange. The resulting temporally enriched features are then integrated into the backbone via another set of cross-attention, enhancing MDTrack’s ability to leverage temporal information. Extensive experiments demonstrate the effectiveness of our proposed method. Both MDTrack-S (Modality-Specific Training) and MDTrack-U (Unified-Modality Training) achieve state-of-the-art performance across five multi-modal tracking benchmarks.