From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets. We argue this inherits more of the generative output interface than dense prediction requires: unlike RGB synthesis, dense prediction asks for pixel-correct, t
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorZanyi Wang →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
- Linked via arxiv authorXin Lin →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
- Linked via arxiv authorHaodong Li →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
- Linked via arxiv authorDengyang Jiang →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
- Linked via arxiv authorYijiang Li →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
- Linked via arxiv authorPengtao Xie →
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models