3701 papers
This paper proposes a real-time two-stream RGB-D object detection model featuring a dynamic RBF-weighted depth-based hyper-involution and a trainable fusion layer to effectively overcome challenges in extracting and combining photometric and depth features, achieving state-of-the-art performance on the NYU Depth V2 benchmark.
This paper proposes a pose-aware in-context visual learning (PA-ICVL) framework that enhances Vision-Language Models' ability to detect semantic structural visual hallucinations in non-photorealistic cartoon images by integrating pose information alongside RGB data, achieving significant performance improvements over RGB-only baselines.
Fuse4Seg introduces a novel bi-level optimization framework for multi-modal medical image fusion that dynamically aligns feature extraction with downstream segmentation tasks through semantic gradients, thereby overcoming the limitations of traditional visual-centric methods to achieve superior tumor boundary preservation and clinical interpretability.
The paper proposes PACE, a novel parameter-efficient fine-tuning method that enhances model generalization and preserves pre-trained knowledge by employing consistency regularization with multiplicative noise to implicitly reduce gradient norms and align fine-tuned models with their pre-trained counterparts.
FALCON is a unified self-supervised pretraining framework for UAV action recognition that overcomes spatial imbalance in aerial footage by combining object-aware masked autoencoding with object-centric dual-horizon future reconstruction, achieving superior accuracy and faster inference without requiring additional preprocessing at test time.
AuthFace is a novel blind face restoration framework that achieves highly authentic results by fine-tuning a text-to-image diffusion model on a curated 1.5K high-resolution professional photography dataset with photography-guided annotations, while employing a time-aware latent facial feature loss to minimize artifacts in critical facial areas.
This paper proposes a self-supervised, lightweight deep learning method that leverages self-consistency learning and inter-component correlations to achieve high-quality reconstruction of irregularly acquired seismic data without requiring external training datasets.
PPLLaVA addresses the computational inefficiency of long-video understanding by introducing a prompt-guided pooling strategy that aggressively compresses visual tokens while preserving instruction-relevant semantics, achieving state-of-the-art performance with up to 18x token reduction.
The paper proposes Ditto, a real-time diffusion-based framework for controllable talking head synthesis that achieves fine-grained motion control and low-latency streaming inference by optimizing a motion-space diffusion transformer to resolve issues of motion-identity disentanglement and internal representation discrepancies.
This paper introduces LEO, a streamlined multimodal large language model architecture that employs a lightweight fusion strategy of post-adaptation projectors, tile-level sequence interleaving, and dynamic tiling to significantly enhance visual understanding across diverse benchmarks and specialized domains like autonomous driving.
FeatureGS enhances 3D Gaussian Splatting by introducing an eigenvalue-based geometric loss term that significantly improves geometric accuracy, reduces floater artifacts and storage requirements by 90%, and enables direct mesh reconstruction while maintaining high photometric quality.
This paper introduces PoI, a framework that enhances Scene Coordinate Regression for visual localization by combining 3D Gaussian Splatting with diffusion-based refinement and a progressive pixel-level filtering strategy to generate and selectively utilize reliable novel views for robust training.
This survey provides a comprehensive overview of the emerging ecosystem of large language models and tools that support researchers across the scientific lifecycle, covering key tasks from literature search and idea generation to content creation, experimentation, and evaluation, while addressing associated datasets, methods, limitations, and ethical concerns.
This paper introduces SCOTT, a sparse convolutional tokenizer combined with a MIM-JEPA training framework, which enables Vision Transformers to learn robust self-supervised representations from scratch on small-scale, fine-grained datasets, thereby challenging the necessity of big data and massive computational resources for effective vision representation learning.
The paper introduces NAMI, a Bridged Progressive Rectified Flow Transformer framework that significantly accelerates image generation and reduces inference time by 64% through a multi-resolution, spatially cascaded architecture with a BridgeFlow module, while maintaining state-of-the-art quality and introducing the NAMI-1K benchmark for evaluation.
ECLARE is an open-source, self-supervised super-resolution method that enhances anisotropic 2D MR volumes by estimating slice profiles and learning in-plane mappings without external data, thereby overcoming domain shift and outperforming existing techniques in both signal recovery and downstream tasks.
The paper introduces EarthScape, a multimodal dataset and reproducible pipeline designed to automate surficial geologic mapping by integrating diverse geospatial data sources, demonstrating that terrain features provide the most robust predictive signal while highlighting the dataset's utility for benchmarking multimodal fusion and domain adaptation.
This paper introduces a new framework of psychophysical tests based on low-level vision principles—specifically contrast sensitivity, masking, and matching—to evaluate and reveal the perceptual strengths and weaknesses of 34 existing image and video quality metrics, demonstrating that standard evaluation protocols often fail to capture these fundamental human visual properties.
FindAnything is an efficient, open-world mapping framework that integrates vision-language features into object-centric volumetric submaps to enable real-time, open-vocabulary semantic understanding of large-scale environments on resource-constrained robots.
This paper proposes GenCLIP, a novel framework for zero-shot anomaly detection that enhances generalization and stability through multi-layer prompting, a dual-branch inference strategy balancing category specificity with generalization, and an adaptive text prompt filtering mechanism.