AI Paper Atlas

Research map / Video / Video generation

VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models

Taesung Kwon, Jong Chul Ye

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 7 citations (OpenAlex)

Read the paper

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
initialize with pseudo-batch inversion of the measurement instead of batch-consistent noise (ablation)VISION-XL · Pexels landscape SR+FVD: 707.7 -> 184.8Improved
initialize with pseudo-batch inversion instead of random noise (ablation)VISION-XL · Pexels landscape SR+PSNR: 29.43 -> 30.74Improved
use pseudo-batch inversion to cut sampling time (ablation)VISION-XL · Pexels landscape SR+sampling time (min): 8.3 -> 2.5Improved
raise inversion timestep from 0.15T to 0.30T (ablation)VISION-XL · Pexels landscape SR+FVD: 229.5 -> 184.8Improved
raise inversion timestep from 0.30T to 0.45T (ablation)VISION-XL · Pexels landscape SR+FVD: 184.8 -> 288.7Hurt
increase CG update steps from 1 to 10 (ablation)VISION-XL · Pexels landscape SR+FVD: 1150 -> 184.8Improved
increase CG update steps from 10 to 20 (ablation)VISION-XL · Pexels landscape SR+FVD: 184.8 -> 486.1Hurt
add scheduled low-pass filtering before re-encoding (ablation)VISION-XL · Pexels landscape SR+FVD: 209.7 -> 184.8Improved
use latent SDXL pseudo-batch method instead of pixel-space SVI for pixel-wise random inpaintingVISION-XL · DAVIS Inpaint+PSNR: 29.60 -> 28.81Hurt
use VISION-XL instead of SVI for deblurring with frame averagingVISION-XL · DAVIS Deblur+FVD: 638.9 -> 228.6Improved
use pseudo-batch sampling instead of 16-frame batch samplingVISION-XL · 25-frame 768x1280 videomemory (GB): 18.5 -> 12.7Improved

Later papers that compared with this method

4 later accepted papers report VISION-XL as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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