high-resolution images
High-resolution images are images with a large number of pixels, allowing for greater detail and clarity. In AI, they can improve the performance of computer vision models, which may require higher fidelity data for tasks like image classification or generation.
- CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
- DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding
- FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning
- GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset
- GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
- Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need
- Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
- MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
- PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
- Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling