1863 papers
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.
This paper introduces ENIGMA-360, a publicly released, temporally synchronized ego-exo dataset containing 360 annotated procedural videos from real industrial scenarios to advance human behavior understanding and establish baselines for tasks like action segmentation and interaction detection.
This paper introduces LAP, a novel procedure planning model that leverages a fine-tuned Vision Language Model to convert visual observations into distinctive text embeddings for a diffusion-based planner, achieving state-of-the-art performance on multiple benchmarks by effectively resolving visual ambiguities through language.
LogoDiffuser is a training-free method that leverages multimodal diffusion transformers and letter-aware attention control to generate high-quality, multilingual logo designs by inputting target characters as images to preserve structural integrity while applying creative styles.
This paper introduces PanoAffordanceNet, a novel framework and the first high-quality dataset (360-AGD) designed to enable holistic affordance grounding in 360-degree indoor environments by addressing challenges like geometric distortion and semantic dispersion through distortion-aware calibration and multi-level constraints.
The paper proposes "Ego," an efficient personalization method for vision-language models that extracts visual tokens representing target concepts via internal attention mechanisms to serve as memory, enabling strong performance across single-concept, multi-concept, and video personalization tasks without requiring additional training stages or external modules.