AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond

Xin Qiao, Matteo Poggi, Xing Wei, Pengchao Deng, Yanhui Zhou, Stefano Mattoccia

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 4 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 fractional calculus (fractional-order dynamics) (ablation)LFRD2 · RUD-ToFMAE: 17.00 -> 16.73Improved
add continuous convolution (ablation)LFRD2 · RUD-ToFMAE: 16.88 -> 16.73Improved
use proposed continuous convolution instead of NFC (ablation)LFRD2 · RUD-ToFMAE: 16.97 -> 16.73Improved
use variable learned fractional order instead of fixed order 0.1 (ablation)LFRD2 · RUD-ToFMAE: 18.12 -> 17.62Improved
use variable learned fractional order instead of fixed order 0.7 (ablation)LFRD2 · RUD-ToFMAE: 19.01 -> 17.62Improved
drop depth from continuous convolution inputs (ablation)LFRD2 · RUD-ToFMAE: 16.91 -> 16.73Improved
add LFRD2 on PE-ToF as initial state builderPE-ToF · RUD-ToFMAE / RMSE: 21.2 / 48.7 -> 20.0 / 33.7Improved
add LFRD2 on UD-ToFnet as initial state builderUD-ToFnet · RUD-ToFMAE / RMSE: 17.3 / 31.1 -> 16.7 / 30.9Improved
add GRU iterative refinement instead of LFRD2UD-ToFnet · RUD-ToFMAE / RMSE: 17.29 -> 17.02; 31.11 -> 31.09Mixed
add LSTM iterative refinement instead of LFRD2UD-ToFnet · RUD-ToFMAE / RMSE: 17.29 -> 16.96; 31.11 -> 31.22Mixed
add NLSPN diffusion refinementUD-ToFnet · RUD-ToFMAE: 17.29 -> 17.23No clear effect
apply LFRD2 to depth super-resolution at 16xDSR-EI · NYUv2MSE: 57.0 -> 52.3Improved

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