AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Interpreting Low-Level Vision Models With Causal Effect Maps

Jinfan Hu, Jinjin Gu, Shiyao Yu, Fanghua Yu, Zheyuan Li, Zhiyuan You, Chaochao Lu, Chao Dong

TPAMI 2025 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 16 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
use Flickr2K instead of DIV2K as natural image library (ablation)CEM · SR, SwinIRpositive effect patches (%): 22.85 -> 23.24No clear effect
use Flickr2K instead of DIV2K as natural image library (ablation)CEM · SR, RCANpositive effect patches (%): 31.07 -> 30.85No clear effect
use Flickr2K instead of DIV2K as natural image library (ablation)CEM · SR, SRResNetpositive effect patches (%): 7.04 -> 7.05No clear effect
use density-based sampling instead of uniform sampling in accelerated CEM (ablation)CEM C3F50 · SRsimilarity score (%): 77.72 -> 82.62Improved
use 3 coarse interventions instead of 1 (ablation)CEM C1F50 · SRsimilarity score (%): 75.86 -> 82.62Improved
increase fine-stage interventions from 10 to 50 (ablation)CEM · SRsimilarity score (%): 65,32 -> 82.62Improved
increase fine-stage interventions from 30 to 50 (ablation)CEM · SRsimilarity score (%): 78.68 -> 82.62Improved
use transformer architecture (X-Restormer) vs SRCNN for SRSR models · SRpositive effect patches (%): 3.06 -> 38.27Improved
compare denoising to super-resolution with same architecture (SwinIR)SwinIR · DN vs SRpositive effect patches (%): 22.85 -> 4.85Hurt
take intervention patches from the input image itself instead of a natural image library (ablation)CEM · SRCEM mapHurt

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