2768 papers
The paper presents GS-2M, a material-aware framework that jointly optimizes 3D Gaussian Splatting attributes and employs a novel roughness supervision strategy to achieve high-fidelity mesh reconstruction of reflective surfaces without relying on complex neural components or external priors.
This paper introduces FAMDA, a simple yet effective unsupervised domain adaptation framework that leverages Vision Foundation Models as teachers within a self-training paradigm to generate high-quality pseudo-labels, enabling the training of highly efficient student networks that achieve state-of-the-art performance in multi-task dense prediction for resource-constrained robotics applications.
QuantSparse is a unified framework that effectively combines model quantization and attention sparsification for video diffusion transformers by introducing Multi-Scale Salient Attention Distillation and Second-Order Sparse Attention Reparameterization to mitigate information loss, thereby achieving significant storage reduction and inference acceleration while substantially outperforming existing baselines in generation quality.
The paper introduces DualFlow, a unified framework that leverages rectified flow and a retrieval-augmented generation module to efficiently produce high-quality, semantically grounded, and rhythmically synchronized two-person 3D motion conditioned on diverse inputs like text, music, and prior sequences.
This paper introduces PHASE-Net, a lightweight and theoretically grounded remote photoplethysmography model that leverages hemodynamic principles to derive a causal Temporal Convolutional Network, enhanced by novel spatial mixing and filtering modules to achieve state-of-the-art accuracy and efficiency in non-contact physiological monitoring under challenging conditions.
This paper introduces LMOD+, a large-scale multimodal ophthalmology benchmark dataset and evaluation framework featuring 32,633 annotated instances across 12 conditions and 5 imaging modalities, designed to advance and systematically assess the capabilities of multimodal large language models in vision-threatening disease diagnosis, staging, and bias detection.
The paper introduces REVEL, a new task for streaming, fine-grained interactive video manipulation on any object at any time, and proposes DragStream, a training-free method that resolves latent distribution drift and context interference in autoregressive video diffusion models through adaptive distribution self-rectification and spatial-frequency selective optimization.
The paper introduces AR-Drag, a reinforcement learning-enhanced few-step autoregressive video diffusion model that achieves real-time, high-fidelity image-to-video generation with diverse motion control while significantly reducing latency compared to existing bidirectional approaches.
This systematic scoping review synthesizes thirty-three studies on unsupervised deep generative models for neuroimaging anomaly detection, highlighting their potential for pathology-agnostic localization in data-scarce settings while identifying key challenges such as methodological heterogeneity and limited external validation.
This paper introduces the Continual Audio-Visual Segmentation (CAVS) task and proposes a Collision-based Multi-modal Rehearsal (CMR) framework that effectively addresses multi-modal semantic drift and co-occurrence confusion through novel sample selection and frequency adjustment strategies, significantly outperforming existing single-modal continual learning methods.
This paper introduces Dream4Drive, a novel synthetic data generation framework that leverages 3D-aware guidance and a fine-tuned driving world model to create diverse, multi-view corner cases, effectively enhancing downstream perception tasks in autonomous driving without the performance gains being negated by increased training epochs.
MoE-GS introduces a novel Mixture-of-Experts framework for dynamic Gaussian Splatting that utilizes a Volume-aware Pixel Router to adaptively blend heterogeneous deformation priors for superior novel view synthesis, while addressing efficiency concerns through multi-expert rendering optimizations and knowledge distillation.
The paper introduces AnyPcc, a universal point cloud compression framework that achieves state-of-the-art performance across diverse datasets by combining a robust Universal Context Model with an Instance-Adaptive Fine-Tuning strategy to effectively handle varying data densities and out-of-distribution scenarios.
This paper proposes an automated pest counting system for water traps that utilizes a robotic arm with adaptive-speed stirring and a confidence-driven closed-loop control mechanism to effectively mitigate occlusion, significantly reducing counting errors and execution time compared to static image methods and constant-speed stirring.
This paper introduces CountFormer, a transformer-based framework that leverages the DINOv2 foundation model to improve structural consistency and reduce overcounting errors in exemplar-free object counting, achieving competitive performance on the FSC-147 benchmark.
SAGE is a zero-shot, structure-aware generative framework that synthesizes visually coherent and motion-consistent video transitions between diverse clips by combining line maps and motion flow guidance with generative synthesis, effectively outperforming existing classical and generative methods without requiring fine-tuning or specific training data.
This paper proposes a forensic method called "diffusion snap-back reconstruction," which detects AI-generated images by analyzing how perceptual similarity metrics change when an image is perturbed and reconstructed by a diffusion model, achieving high accuracy (AUROC of 0.993) and robustness against common distortions without relying on traditional pixel-level artifacts.
This paper introduces "Jr. AI Scientist," an autonomous system that mimics a novice researcher's workflow to generate novel, scientifically valuable papers building on real academic works, while simultaneously evaluating its performance through rigorous automated and human assessments to identify both its capabilities and the significant risks and limitations of current AI-driven scientific exploration.
This paper introduces MUGSQA, a novel framework comprising a multi-uncertainty-based Gaussian Splatting quality assessment dataset, a unified multi-distance subjective evaluation method, and two benchmarks designed to rigorously assess the robustness of reconstruction methods and the performance of existing quality metrics under varying input conditions.
This paper introduces CountOCC, a novel amodal counting framework that overcomes the limitations of existing methods under occlusion by hierarchically reconstructing complete object features through multimodal guidance and visual equivalence objectives, achieving state-of-the-art performance on newly established occlusion-augmented benchmarks.