AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation

Akshay Krishnan, Xinchen Yan, Vincent Casser, Abhijit Kundu

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 20 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 joint latent space (vs disentangled latents) (ablation)Orchid · COCO text-conditionedCLIP: 0.312 -> 0.316Improved
add joint latent space (vs disentangled latents) (ablation)Orchid · COCO text-conditionedLPIPS: 0.769 -> 0.764Hurt
add joint latent space (vs disentangled latents) (ablation)Orchid · NYUv2 normalsaccuracy within 11.25 deg: 54.8 -> 60.6Improved
add joint latent space (vs disentangled latents) (ablation)Orchid · NYUv2 depthdelta1: 96.0 -> 96.9Improved
add VAE distillation loss (ablation)Orchid · COCO text-conditionedCLIP: 0.309 -> 0.316Improved
add VAE distillation loss (ablation)Orchid · NYUv2 normalsaccuracy within 11.25 deg: 54.6 -> 60.6Improved
add VAE distillation loss (ablation)Orchid · NYUv2 depthdelta1: 96.1 -> 96.9Improved
add pseudo depth-normal labels on text-image data (ablation)Orchid · NYUv2 normalsaccuracy within 11.25 deg: 57.9 -> 60.6Improved
add pseudo depth-normal labels on text-image data (ablation)Orchid · NYUv2 depthdelta1: 96.6 -> 96.9Improved
joint diffusion instead of Diff+Diff or Diff+FF pipelinesOrchid · inference timeseconds per image: 4.2 -> 1.2Improved
joint diffusion instead of color diffusion plus feed-forward depth/normal modelsOrchid · inference timeseconds per image: 1.3 -> 1.2Improved
joint color-depth-normal latent vs separate depth and normal modelsOrchid · KITTI depth-normal consistencyinconsistency error: 0.144 -> 0.082Improved

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