AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Bridging Human Evaluation to Infrared and Visible Image Fusion

Jinyuan Liu, Xingyuan Li, Qingyun Mei, Haoyuan Xu, Zhiying Jiang, Long Ma, Risheng Liu, Xin Fan

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Human-like visual cognition in VLMs · 5 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 reward-model score branch (ablation)EVAFusion · M3FDPSNR: 64.81 -> 65.09Improved
add reward-model heatmap branch (ablation)EVAFusion · M3FDPSNR: 64.93 -> 65.09Improved
add SAM region segmentation (ablation)EVAFusion · M3FDPSNR: 63.02 -> 65.09Improved
add SAM region segmentation (ablation)EVAFusion · TNOCC: 0.48 -> 0.51Improved
add reward-model score branch (ablation)EVAFusion · TNOCC: 0.50 -> 0.51No clear effect
use GRPO with regional advantages instead of DPO (ablation)EVAFusion · TNOPSNR: 63.98 -> 65.43Improved
use GRPO instead of PPO (ablation)EVAFusion · TNOPSNR: 63.59 -> 65.43Improved
fine-tune with PPO versus baseline (ablation)DCEvo · TNOPSNR: 63.83 -> 63.59Hurt
fine-tune with DPO versus baseline (ablation)DCEvo · RoadScenePSNR: 59.66 -> 61.50Improved
add RLHF fine-tuning with human-feedback rewardDCEvo · RoadScenePSNR: 59.66 -> 61.84Improved
add RLHF fine-tuning with human-feedback rewardDCEvo · M3FD detectionmAP: 58.23 -> 62.23Improved
add RLHF fine-tuning with human-feedback rewardDCEvo · TNONIQE: 6.25 -> 5.37Improved

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