AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

LUA: Latent Upscaling Adapter for Diffusion-Based Image Synthesis

Aleksandr Razin, Kazantsev Danil, Ilya Makarov

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 0 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 Stage III edge-aware pixel refinement (ablation)LUA curriculum · OpenImages val (x2)PSNR: 28.96 -> 32.54Improved
add Stage II joint latent-pixel consistency (ablation)LUA curriculum · OpenImages val (x2)PSNR: 31.05 -> 32.54Improved
add Stage I latent structural alignment (ablation)LUA curriculum · OpenImages val (x2)PSNR: 31.60 -> 32.54Improved
add pixel-domain stages to latent l1-only training (ablation)LUA curriculum · OpenImages val (x4)LPIPS: 0.236 -> 0.184Improved
use joint multi-head instead of separate x2 specialist (ablation)LUA · OpenImages val (x2)PSNR: 31.92 -> 32.54Improved
use joint multi-head instead of separate x4 specialist (ablation)LUA · OpenImages val (x4)PSNR: 27.71 -> 27.94Improved
use pixel-shuffle heads instead of implicit LIIF upsampler (ablation)LUA · OpenImages val (x2)PSNR: 29.10 -> 32.54Improved
replace pixel-space SwinIR with latent-space LUASDXL 1024 base · OpenImages 2048x2048FID: 183.16 -> 180.80Improved
replace direct high-res sampling with LUA upscalingSDXL · OpenImages 4096x4096FID: 280.42 -> 176.90Improved
replace direct SDXL sampling with LUA at 1KSDXL · OpenImages 1024x1024FID: 194.53 -> 209.80Hurt
replace SwinIR with LUA at 1KSDXL · OpenImages 1024x1024pFID: 204.23 -> 191.75Improved
increase fine-tuning pairs for cross-VAE transfer from 10k to 500kLUA on SDXL · OpenImages 2048x2048FID: 203.1 -> 180.80Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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