AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

FLINT: Coupling Proximal Initialization and Bounded Stochasticity for Flow-Matching Inverse Problems

Junseo Bang, daewon choi, Dong Ju Mun, Se Young Chun

NeurIPS 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 0 citations (OpenAlex)

Read the paper

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes FLINT, a flow-matching inverse-problem solver that couples proximal initialization of the source noise with bounded stochasticity in the sampling trajectory.

Problem

Generative posterior sampling for imaging inverse problems with flow matching models, where existing solvers split into trajectory-space refinement and source-space (initial noise) optimization that are treated as independent design choices.

Approach

Argues that trajectory-space and source-space methods are fundamentally coupled and combines proximal initialization of the initial noise with bounded stochasticity during sampling, rather than treating the two as independent choices.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add manifold-constrained proximal initialization (Stage 1) instead of random noise (ablation)FLINT · Gaussian deblurring FFHQ (100)PSNR: 28.56 -> 29.60Improved
Add manifold-constrained proximal initialization instead of random noise (ablation)FLINT · Gaussian deblurring FFHQ (100)LPIPS: 0.327 -> 0.218Improved
Add spectrally weighted data consistency (Wiener weighting) (ablation)FLINT Stage 1 · Gaussian deblurring FFHQ (100)PSNR: 29.60 -> 30.11Improved
Add spectrally weighted data consistency (ablation)FLINT Stage 1 · Gaussian deblurring FFHQ (100)KID: 0.008 -> 0.005Improved
Use moderate stochasticity magnitude lambda_s=0.8 vs 0.3 (ablation)FLINT Stage 2 · Gaussian deblurring FFHQ (100)PSNR: 29.59 -> 30.11Improved
Use excessive stochasticity lambda_s=1.8 vs 0.8 (ablation)FLINT Stage 2 · Gaussian deblurring FFHQ (100)LPIPS: 0.192 -> 0.328Hurt
Use bell-shaped instead of front-loaded stochasticity schedule (ablation)FLINT Stage 2 · Gaussian deblurring FFHQ (100), lambda_s=1.8LPIPS: 0.499 -> 0.328Improved
Use bell-shaped instead of front-loaded schedule at small magnitude (ablation)FLINT Stage 2 · Gaussian deblurring FFHQ (100), lambda_s=0.3PSNR: 29.60 -> 29.59No clear effect
Perturb proximal initialization within sufficiency regime (C0 up to about 0.4) (ablation)FlowDPS with SLERP-perturbed inversion · Gaussian deblurring FFHQ (100)PSNR/LPIPSNo clear effect
Increase cumulative stochasticity G during guided sampling (ablation)FlowDPS · Gaussian deblurring FFHQ (100)reconstruction qualityHurt
Combine FLINT with 30 total NFEs vs baselines at 50 NFEsFLINT · FFHQ SR x8, Gaussian deblurringPSNR, LPIPSImproved
Apply FLINT to Stable Diffusion 1.5FLINT · FFHQ SR x4 (200 NFE)FID: 37.35 -> 22.36Improved

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