Dense scene composition and instance fidelity in synthetic diffusion images drive better segmentation performance; SENSE framework exploits this to improve models on Cityscapes, COCO, and ADE20K.
Diffusion-4k: Ultra-high-resolution image synthesis with latent diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PixVerve introduces a 95K ultra-high-resolution image-text dataset and training strategies that enable native 100-megapixel text-to-image generation together with a new evaluation benchmark.
citing papers explorer
-
What Makes Synthetic Data Effective in Image Segmentation
Dense scene composition and instance fidelity in synthetic diffusion images drive better segmentation performance; SENSE framework exploits this to improve models on Cityscapes, COCO, and ADE20K.
-
PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset
PixVerve introduces a 95K ultra-high-resolution image-text dataset and training strategies that enable native 100-megapixel text-to-image generation together with a new evaluation benchmark.