AI Paper Atlas

Research map / 3D vision / Depth and stereo

RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching

Zhen Liu, Diedong Feng, Hai Jiang, Liaoyuan Zeng, Hao Wang, Chaoyu Feng, Lei Lei, Bing Zeng, Shuaicheng Liu

AAAI 2026 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 1 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 dual-domain feature alignment loss L_fea to the RAW autoencoder (ablation)DLAE · RAW autoencoder reconstructionPSNR: 25.36 -> 32.94Improved
inject RGB encoder features into the RAW autoencoder (ablation)DLAE · RAW autoencoder reconstructionPSNR: 20.08 -> 25.36Improved
inject RGB features without alignment loss, final RAW reconstruction (ablation)RAW-Flow · FiveK-Nikon reconstructed RAWPSNR: 29.19 -> 28.48Hurt
use deterministic latent flow matching instead of standard diffusion (ablation)RAW-Flow · FiveK-NikonPSNR: 28.30 -> 30.79Improved
start flow from RGB latent instead of Gaussian noise (ablation)RAW-Flow · FiveK-CanonPSNR: 22.74 -> 32.55Improved
use cross-scale context guidance instead of single-scale context (ablation)RAW-Flow · FiveK-CanonPSNR: 28.43 -> 32.55Improved
use cross-scale context guidance instead of RGB latent guidance (ablation)RAW-Flow · FiveK-NikonPSNR: 28.50 -> 30.79Improved
flow matching vs best regression baseline (ReRAW-S)FiveK-Nikon · FiveK-NikonPSNR (RAW): 28.04 -> 30.79Improved
RAW-Flow vs ReRAW-S on PASCALRAW SSIMPASCALRAW · PASCALRAWSSIM (RAW): 0.9854 -> 0.9831Hurt
diffusion-based methods vs best regression methodRGB-to-RAW baselines · FiveK-NikonPSNR (RAW): 26.96 vs 28.04No clear effect

Later papers that compared with this method

1 later accepted paper reports RAW-Flow as a baseline in their results tables; 1 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