AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Curved Diffusion: A Generative Model With Optical Geometry Control

Andrey Voynov, Amir Hertz, Moab Arar, Shlomi Fruchter, Daniel Cohen-Or

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add per-pixel coordinate conditioning fine-tuning to a base text-to-image modelLDM base model · MS-COCO FIDFID: 17.5 -> 17.5No clear effect
Add self-attention score reweighting by warped density (ablation)Curved Diffusion · corner-squeezing warp, 100 prompts x 8 imagessaliency center alignment of unwarped imagesImproved
Condition on per-pixel warp field instead of writing 'fisheye' in the prompt (ablation)Curved Diffusion · fisheye lens geometrygeometric alignment (qualitative)Improved
Generate with the model instead of post-hoc warping a regular image onto a sphereSphere texturing · sphere texture human studypreference (%): 12% (base) -> 58%Improved
Use metric tensor conditioning instead of positional conditioning for sphere textures (ablation)Curved Diffusion · sphere texture human studypreference (%): 28% -> 40%Improved
Add distance-to-center conditioning to metric-conditioned model (ablation)Metric-conditioned model · sphere panoramaimage quality (qualitative)Improved
Use flipped upside-down coordinate gridCurved Diffusion · out-of-training-distribution warplocal fidelity (qualitative)Hurt
Apply conditioning to strong fish-eye warp, compare unwarping error with manually distorted base outputsCurved Diffusion · distortion fidelity, k1 in 10-25undistortion displacement errorNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy