AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction

Jiaming Liu, Rushil Anirudh, Jayaraman J. Thiagarajan, Stewart He, K Aditya Mohan, Ulugbek S. Kamilov, Hyojin Kim

ICCV 2023 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 122 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
condition the diffusion model on limited-angle reconstruction and use DOLCE instead of unconditionally trained diffusion (DPS)DOLCE · Body CT, 60 degPSNR (dB): 28.97 -> 35.11Improved
add proximal data-consistency step during sampling (ablation)DOLCE (RLS condition) · Body CT, 120 degPSNR (dB): 41.25 -> 42.52Improved
add proximal data-consistency step during sampling (ablation)DOLCE (RLS condition) · Luggage CT, 90 degPSNR (dB): 38.64 -> 39.28Improved
use RLS instead of FBP as the conditional input (ablation)DOLCE · Body CT, 60 degPSNR (dB): 34.05 -> 35.15Improved
average multiple samples (DOLCE-SA) (ablation)DOLCE · Body CT, 60 degPSNR (dB): 35.11 -> 35.58Improved
train one DOLCE model jointly on luggage and medical data instead of separate models (ablation)DOLCE · Luggage and body CT, 60 to 120 degPSNR/SSIM: 33.59 -> 33.98 (luggage 60 deg)No clear effect
test on a different distribution than trained (model trained on medical, tested on luggage) (ablation)DOLCE · Luggage CT, 60 degPSNR (dB): 33.59 -> 26.78Hurt
replace uniform schedule with cosine noise schedule during training (ablation)DOLCE · CT reconstructionimage reconstruction qualityNo clear effect
test with unseen angular range (45 deg) not seen in trainingDOLCE · Body CT, 45 degPSNR (dB): 24.50 -> 24.97 (DPS vs DOLCE)Improved
increase number of sampling steps K (ablation)DOLCE · Body CTPSNRImproved

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