AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

NanoSD: Edge Efficient Foundation Model for Real Time Image Restoration

Subhajit Sanyal, Srinivas Soumitri Miriyala, Akshay Janardan Bankar, Manjunath Arveti, Sowmya Vajrala, Shreyas Pandith, Sravanth Kodavanti, Abhishek Ameta, Harshit Harshit, Amit Satish Unde

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 3 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
use NanoSD-Prime (block-searched U-Net) instead of hand-tuned SD 1.5 variant (ablation)SD 1.5 U-Net · teacher-aligned FIDtaFID: 20.6 -> 10Improved
use NanoSD 2 instead of TinySDSD 1.5 U-Net · NPU latencylatency (ms): 74 -> 27Improved
use NanoSD 2 instead of TinySDSD 1.5 U-Net · teacher-aligned FIDtaFID: 13.8 -> 10Improved
use NanoSD 1 instead of NanoSD 2 (ablation)NanoSD · NPU latencylatency (ms): 27 -> 41Hurt
use NanoSD backbone in OSDFaceOSDFace · CelebA-TestMACs (G): 2465 -> 479Improved
use NanoSD backbone in OSDFaceOSDFace · CelebA-TestFID: 45.41 -> 45.92No clear effect
use NanoSD backbone in Diff-PluginDiff-Plugin · desnowing, dehazing, deblurring, derainingFID: 34.30 -> 34.83 (desnowing)No clear effect
use NanoSD backbone in Diff-PluginDiff-Plugin · restoration tasksparameters (M): 1256 -> 712Improved
use NanoSD backbone in MarigoldMarigold · NYUv2 zero-shot depthAbsRel: 5.5 -> 7.2Hurt
use NanoSD backbone in MarigoldMarigold · KITTI zero-shot depthAbsRel: 9.9 -> 11.8Hurt
use NanoSD backbone in DiffBIRDiffBIR · CelebA-TestFID: 71.77 -> 70.89No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 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