Paper Detail
Ying Zeng, Miaosen Luo, Guangyuan Li, Yang Yang, Ruiyang Fan, Linxiao Shi, Qirui Yang, Jian Zhang, Chengcheng Liu, Siming Zheng, Jinwei Chen, Bo Li, Peng-Tao Jiang
Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit human instruction of aesthetic intent, which is often ambiguous, incomplete, or inaccessible to non-expert users. In this work, we propose SmartPhotoCrafter, an automatic photographic image editing method which formulates image editing as a tightly coupled reasoning-to-generation process. The proposed model first performs image quality comprehension and identifies deficiencies by the Image Critic module, and then the Photographic Artist module realizes targeted edits to enhance image appeal, eliminating the need for explicit human instructions. A multi-stage training pipeline is adopted: (i) Foundation pretraining to establish basic aesthetic understanding and editing capabilities, (ii) Adaptation with reasoning-guided multi-edit supervision to incorporate rich semantic guidance, and (iii) Coordinated reasoning-to generation reinforcement learning to jointly optimize reasoning and generation. During training, SmartPhotoCrafter emphasizes photo-realistic image generation, while supporting both image restoration and retouching tasks with consistent adherence to color- and tone-related semantics. We also construct a stage-specific dataset, which progressively builds reasoning and controllable generation, effective cross-module collaboration, and ultimately high-quality photographic enhancement. Experiments demonstrate that SmartPhotoCrafter outperforms existing generative models on the task of automatic photographic enhancement, achieving photo-realistic results while exhibiting higher tonal sensitivity to retouching instructions. Project page: https://github.com/vivoCameraResearch/SmartPhotoCrafter.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{zeng2026smartphotocrafter,
title = {SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing},
author = {Ying Zeng and Miaosen Luo and Guangyuan Li and Yang Yang and Ruiyang Fan and Linxiao Shi and Qirui Yang and Jian Zhang and Chengcheng Liu and Siming Zheng and Jinwei Chen and Bo Li and Peng-Tao Jiang},
year = {2026},
abstract = {Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit human instruction of aesthetic intent, which is often ambiguous, incomplete, or inaccessible to non-expert users. In this work, we propose SmartPhotoCrafter, an automatic photographic image editing method which formulates image editing as a tightly coupled reas},
url = {https://huggingface.co/papers/2604.19587},
keywords = {image quality comprehension, Photographic Artist module, Image Critic module, multi-stage training pipeline, foundation pretraining, adaptation with reasoning-guided multi-edit supervision, coordinated reasoning-to-generation reinforcement learning, photo-realistic image generation, image restoration, retouching tasks, semantic guidance, huggingface daily},
eprint = {2604.19587},
archiveprefix = {arXiv},
}
{}