AI Paper Atlas

Research map / Image generation / Super-resolution

Inf-DiT: Upsampling any-resolution image with memory-efficient diffusion transformer.

Zhuoyi Yang, Heyang Jiang, Wenyi Hong, Jiayan Teng, Wendi Zheng, Yuxiao Dong, Ming Ding, Jie Tang

ECCV 2024 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 13 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 unidirectional block attention between blocks (ablation)Inf-DiT · HPDv2 2048x2048FID_crop: 83.7 -> 71.9Improved
add nearby LR cross attention (ablation)Inf-DiT · HPDv2 2048x2048FID_crop: 73.6 -> 71.9Improved
add CLIP image embedding semantic input (ablation)Inf-DiT · HPDv2 2048x2048FID_crop: 72.8 -> 71.9Improved
add semantic input (ablation)Inf-DiT · HPDv2 2048x2048FID: 66.2 -> 66.0No clear effect
use Inf-DiT instead of BSRGAN at 4096x4096SDXL upsampling · HPDv2 4096x4096FID: 66.0 -> 67.0Hurt
use Inf-DiT instead of UNet SDXL architecture for 4096x4096 inferenceupsampler architecture · memory at 4096x4096GPU memory: more than 5x memory savedImproved
use Inf-DiT instead of Real-ESRGAN on DIV2K variable resolutionsuper-resolution · DIV2KFID: 35.0 -> 20.2 (vs BSRGAN)Improved
add iterative upsampling for 64x upscale from 32x32Inf-DiT · iterative upsampling (qualitative)error accumulationHurt

Later papers that compared with this method

1 later accepted paper reports Inf-DiT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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