AI Paper Atlas

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

Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion

Jiwon Kim, Pureum Kim, SeonHwa Kim, Soobin Park, Eunju Cha, Kyong Hwan Jin

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 0 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 DRF (use DRF instead of Ctrl-X alone)Ctrl-X · All structure typessuccessive rate: 0.9577 -> 0.9859Improved
use DRF instead of Ctrl-XCtrl-X · Pose structureDINO-I: 0.7378 -> 0.7391No clear effect
use DRF instead of Ctrl-XCtrl-X · Canny structureDINO-I: 0.7335 -> 0.7135Hurt
use DRF instead of Ctrl-XCtrl-X · Point cloud structureDINO Self-Sim: 0.1205 -> 0.1114Improved
use DDIM 40 steps with DRF replaced by DPM-Solver++ 10 steps (ablation)DRF with DDIM · Scheduler studyTime (s): 47.87 -> 15.56Improved
apply DRF for 10 steps instead of 20 steps (ablation)DRF · Step ablationinference time (s): 56.87 -> 36.09Mixed
apply DRF at all 50 steps instead of 20 steps (ablation)DRF · Step ablationinference time (s): 56.87 -> 135.07No clear effect
increase DRF iterations N from 1 to 3 (ablation)DRF · Inference efficiencyinference latency (s): 29.69 -> 56.87Mixed
use SD 1.5 backbone instead of SDXL for DRFDRF · Cross-backboneGPU memory (GiB): 18.98 -> 5.87Improved
use SD 2.0 backbone instead of SDXL for DRFDRF · Cross-backboneDINO-I: 0.6957 -> 0.453Hurt
use exponential weighting of generation feedback instead of linear or uniform (ablation)DRF · Weight schedule ablationimage quality (qualitative)Improved
increase recursion depth K beyond 5 (ablation)DRF · Hyper-parameter sweepCLIP, Self-Sim, DINO-INo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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