Text2Stereo adapts Stable Diffusion to generate wide-baseline stereo image pairs from text by fine-tuning with LoRA and a disparity-correlation consistency reward.
Re- inforcement learning for fine-tuning text-to-image diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards
Text2Stereo adapts Stable Diffusion to generate wide-baseline stereo image pairs from text by fine-tuning with LoRA and a disparity-correlation consistency reward.