AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Toward Deeper Emotional Reflection: Crafting Affective Image Filters With Generative Priors

Peixuan Zhang, Shuchen Weng, Jiajun Tang, Si Li, Boxin Shi

TPAMI 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 2 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 content preservation module (ablation)AIF-D · AIF dataset test setSSIM (%): 13.48 -> 57.74Improved
add in-depth emotional reasoning with LLM cues (ablation)AIF-D · AIF dataset test setEAcc (%): 35.87 -> 37.48Improved
add voting ensemble mechanism (ablation)AIF-D · AIF dataset test setEAcc (%): 34.18 -> 37.48Improved
add emotional reflection decoder instead of vanilla decoder (ablation)AIF-D · AIF dataset test setSG (per mille): 1.4639 -> 1.3416Improved
add texture mapping loss instead of standard style loss (ablation)AIF-D · AIF dataset test setSSD: 1.2824 -> 1.1123Improved
add emotional reflection decoder (ablation)AIF-D · AIF dataset test setEAcc (%): 35.21 -> 37.48Improved
switch backbone from transformer AIF-B to diffusion-based AIF-DAIF-B · AIF dataset test setSSIM (%): 56.15 -> 57.74Improved
switch from AIF-B to AIF-DAIF-B · AIF dataset test setEAcc (%): 36.02 -> 37.48Improved
switch from AIF-B to AIF-DAIF-B · AIF user study (AMT, 200 samples)EPS user study (%): 18.52 -> 39.51Improved
set style/content balance gamma to 0.3 instead of 0.1 (ablation)AIF-D · AIF dataset test setEAcc (%): 36.64 -> 37.48Improved
set gamma to 0.3 instead of 3.0 (ablation)AIF-D · AIF dataset test setSSIM (%): 55.11 -> 57.74Improved
set gamma to 0.3 instead of 1.0 (ablation)AIF-D · AIF dataset test setSSD: 1.1679 -> 1.1123Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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