AI Paper Atlas

Research map / 3D vision / Depth and stereo

Bridging RGB and RAW: Single-step Deterministic Flow with Homogeneous Representation Alignment

Diedong Feng, Peiyi Zeng, Zhen Liu, Zhongyang Li, Bing Zeng, Shuaicheng Liu

ICML 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction

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 teacher weight loading and representation alignment (full HRA vs base) (ablation)SHADE · FiveK-NikonPSNR: 28.05 -> 30.89Improved
add teacher weight loading (vs w/o Pretrain) (ablation)SHADE · FiveK-NikonPSNR: 30.01 -> 30.89Improved
add representation alignment (vs w/o Align) (ablation)SHADE · FiveK-NikonPSNR: 29.39 -> 30.89Improved
add representation alignment (vs w/o Align) (ablation)SHADE · PASCALRAWPSNR: 38.60 -> 39.07Improved
add L2 loss (ablation)SHADE · FiveK-NikonPSNR: 29.62 -> 30.89Improved
add log-L1 loss (ablation)SHADE · PASCALRAWPSNR: 35.51 -> 39.07Improved
add log-L1 loss (ablation)SHADE · FiveK-NikonSSIM: 0.8879 -> 0.8858Hurt
add AE reconstruction loss (ablation)SHADE · PASCALRAWPSNR: 36.83 -> 39.07Improved
add DiT reconstruction loss (ablation)SHADE · FiveK-NikonPSNR: 29.21 -> 30.89Improved
single-step deterministic flow instead of standard flow matching (ablation)SHADE · PASCALRAWPSNR: 37.35 -> 39.07Improved
single-step deterministic flow instead of Mean Flow from noise (ablation)SHADE · FiveK-NikonPSNR: 30.38 -> 30.89Improved
single-step deterministic flow instead of direct regression (ablation)SHADE · PASCALRAWPSNR: 37.69 -> 39.07Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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