AI Paper Atlas

Research map / Video / Video segmentation and tracking

Continuous Space-Time Video Super-Resolution with 3D Fourier Fields

Alexander Becker, Julius Erbach, Dominik Narnhofer, Konrad Schindler

ICLR 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution

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
increase number of basis functions from 128 to 256 (ablation)V3 · Adobe240 (Average)PSNR: 30.55 -> 31.55Improved
increase number of basis functions from 256 to 512 (ablation)V3 · Adobe240 (Average)PSNR: 31.55 -> 32.16Improved
increase number of basis functions from 512 to 768 (ablation)V3 · Adobe240 (Average)PSNR: 32.16 -> 32.29No clear effect
learn the basis frequencies instead of fixing a uniform 3D Fourier grid (ablation)V3 · Adobe240 (Average)PSNR: 24.80 -> 32.16Improved
learn the basis frequencies instead of fixing a uniform 3D Fourier grid (ablation)V3 · Vid4PSNR: 22.85 -> 26.72Improved
train with 100% instead of 50% of iterations (ablation)V3 · Vid4 x4PSNR: 26.71 -> 26.76No clear effect
train with 100% instead of 25% of iterations (ablation)V3 · Adobe240 (Average)PSNR: 31.84 -> 32.16Improved
scale encoder attention embedding from 90 to 144 (V3-Large)V3 · Adobe240 (Average)PSNR: 32.29 -> 32.45Improved
joint 3D Fourier field instead of decoupled spatial INR plus flow warpingC-STVSR · Adobe240 frame interpolation (S x1 T x8)PSNR: 29.37 -> 33.43Improved
joint 3D Fourier field compared with frame-by-frame arbitrary-scale image SRV3 · REDS val (spatial x4)PSNR: 28.75 -> 29.92Improved
joint representation lowers temporal inconsistencyV3 · Vid4 (S x4 T x2)tOF: 0.323 -> 0.254Improved
sample with closed-form Gaussian PSF anti-aliasing and joint representation under input noiseV3 · Vid4 with Gaussian noise sigma 5e-2PSNR: 24.53 -> 25.18Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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