1384 papers
This paper proposes a zero-shot MRI super-resolution framework that leverages explicit, physics-driven 3D Gaussian representations and parallel brick-based rasterization to achieve high-quality, efficient reconstruction without relying on costly paired training data.
This paper introduces Quantization-aware Distilled Restoration (QDR), a novel framework that employs Decoder-Free Distillation and Learnable Magnitude Reweighting to overcome bottlenecks in quantization-aware training, enabling high-performance, edge-deployed image restoration models that achieve near-FP32 accuracy and significant speedups.
This paper proposes a vision-language grounded framework for interpretable synthetic data generation and evaluation in remote sensing, introducing the ARAS400k dataset which demonstrates that augmenting real data with synthetic images consistently outperforms real-data-only baselines in semantic segmentation and image captioning tasks.
This paper introduces X-GS, an extensible open framework that unifies 3D Gaussian Splatting with downstream multimodal models through a real-time, semantically enriched pipeline capable of processing unposed video streams for tasks like object detection and zero-shot captioning.
This paper presents OTPL-VIO, a robust stereo visual-inertial odometry system that enhances performance in low-texture and illumination-challenging environments by employing a training-free deep descriptor with entropy-regularized optimal transport for line association and introducing adaptive uncertainty weighting to stabilize estimation.
KV-Lock is a training-free framework for DiT-based video diffusion models that dynamically adjusts background key-value locking and classifier-free guidance scales based on hallucination detection to simultaneously enhance foreground quality and maintain background consistency.
The paper presents DiffWind, a physics-informed differentiable framework that unifies wind-object interaction modeling, video-based reconstruction, and forward simulation by combining 3D Gaussian Splatting, the Material Point Method, and Lattice Boltzmann constraints to accurately recover and simulate wind-driven object dynamics from video observations.
VarSplat is an uncertainty-aware 3D Gaussian Splatting SLAM system that explicitly learns per-splat appearance variance to render differentiable uncertainty maps, thereby guiding tracking and optimization toward reliable regions to achieve robust pose estimation and high-fidelity reconstruction in challenging real-world environments.
This paper introduces FootMR, a method that refines 3D foot motion in markerless monocular human motion capture by lifting 2D keypoints to 3D using large-scale motion capture data and context-aware residual prediction, alongside the new MOOF dataset, to significantly outperform existing state-of-the-art approaches in accuracy and generalization.
This paper introduces AutoViVQA, a large-scale automatically constructed dataset for Vietnamese Visual Question Answering, and evaluates transformer-based multimodal models alongside various automatic metrics to assess their performance and alignment with human judgment in the Vietnamese context.
This paper introduces DRIFT, a dual-path Transformer model that effectively fuses fine-grained local and coarse-grained global features from sparse 4D radar point clouds to achieve state-of-the-art performance in automated driving perception tasks like object detection and free road estimation.
The paper introduces TemporalDoRA, a parameter-efficient fine-tuning method that integrates lightweight temporal attention into the low-rank adaptation branch of vision encoders to enhance robustness against linguistic variations in surgical video question answering, validated by a new colonoscopy dataset and improved Out-of-Template performance.
The paper proposes TriFusion-SR, a wavelet-guided conditional diffusion framework that jointly performs tri-modal medical image fusion and super-resolution by decomposing features into frequency bands and employing rectified wavelet features with adaptive spatial-frequency fusion to achieve state-of-the-art performance in resolution and perceptual quality.
ProGS introduces a novel streaming-friendly codec that organizes 3D Gaussian Splatting data into an octree structure with mutual information enhancement, achieving a 45-fold reduction in file size and over 10% visual improvement while enabling progressive coding for varying bandwidth conditions.
This paper introduces GSStream, a novel volumetric scene streaming system for 3D Gaussian Splatting that leverages collaborative viewport prediction and deep reinforcement learning-based bitrate adaptation to overcome bandwidth challenges and deliver high-quality, real-time immersive experiences.
The paper proposes FrameDiT, a novel video generation architecture that introduces Matrix Attention to efficiently model global spatio-temporal dynamics by processing frames as matrices, thereby achieving state-of-the-art video quality and temporal coherence while maintaining computational efficiency comparable to local factorized attention.
This paper introduces EXPLORE-Bench, a benchmark derived from real first-person videos to evaluate the ability of multimodal large language models to perform long-horizon egocentric scene prediction, revealing significant performance gaps compared to humans and demonstrating that stepwise reasoning offers partial improvements at a computational cost.
FetalAgents is a novel multi-agent system that dynamically orchestrates specialized vision experts to deliver robust, end-to-end fetal ultrasound analysis and structured clinical reporting across multiple tasks, outperforming existing specialized models and multimodal large language models.
The paper introduces -Occ, a robust 3D semantic occupancy prediction framework that leverages a Multi-view Masked Reconstruction module and a Feature Memory Module to maintain geometric and semantic coherence under incomplete multi-camera inputs, significantly outperforming existing methods in scenarios with missing views.
This paper introduces Step-Aware Contrastive Alignment (SACA), a novel framework that enhances Vision-Language Navigation in Continuous Environments by utilizing a perception-grounded auditor to extract dense, step-level supervision from imperfect trajectories, thereby overcoming the limitations of compounding errors in supervised fine-tuning and sparse rewards in reinforcement fine-tuning to achieve state-of-the-art performance.