- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes ASAP, which achieves this by locally degrading images of the human body structure in a reasonable manner, constructing preference data with clear anatomical errors, and combining the preference optimization objective of region weighting and limited intervals to enhance the rationality of the generated image's human body structure. The authors also constructed the HAP dataset and the HAF-Bench evaluation benchmark. Experiments show that this method can effectively reduce the anatomical error rate of the human body on FLUX and SDXL, while maintaining good overall image quality.
Critical strengths
- The problem is of practical significance. By leveraging local synthesis preferences to construct targeted supervision signals for local anatomical errors in human body image generation, the approach is logically sound.
- The method design is relatively comprehensive, integrating data construction, region-aware optimization, and evaluation benchmarks, and has certain practical value.
- The experiments are sufficiently comprehensive, covering different generation models, baseline comparisons, ablation experiments, and manual evaluations, and the results as a whole support the effectiveness of the method.
Critical weaknesses
- The method is relatively limited in terms of innovation. Both the regional weighting and the finite interval optimization are based on existing ideas, and their main contributions lie in the combination and application for solving human anatomy problems.
- There may be a distribution difference between the synthetic anatomical errors and the errors naturally generated by the real generation model. The analysis of this issue in the paper is still insufficient.
- HAF-Bench mainly relies on visual language models for automatic evaluation. Although it provides manual verification, further explanations are needed regarding the reliability and generalization ability of the evaluation results.
Questions for authors
- Will the types and degrees of synthetic degradation affect the model's generalization ability for real anatomical errors?
- Can we further analyze the improvement extent on different anatomical regions or error types?
- It is suggested to add a direct comparison with existing region-aware preference optimization methods to more clearly demonstrate the contribution of the optimization objective itself.
2 comments
W2 & Q1 & Q2: There may be a distribution difference between the synthetic anatomical errors and the errors naturally generated by the real generation model. The analysis of this issue in the paper is still insufficient.
Will the types and degrees of synthetic degradation affect the model's generalization ability for real anatomical errors?
Can we further analyze the improvement extent on different anatomical regions or error types?
Synthetic vs. Naturally Generated Errors
We provide qualitative comparisons of synthetic and naturally generated errors and conduct separate training experiments with hand-only and face-only degradation to examine how the targeted anatomical region affects performance.
We agree that the potential distribution gap between synthetic and naturally generated anatomical errors is important. This gap affects the quality of synthetic localized preferences and the training signal they provide during preference optimization. We considered this issue during our experiments and provide qualitative examples of both types of errors in Appendix Figure 7.
To examine the effect of the anatomical types targeted by synthetic degradation, we trained separate models using preference pairs with degradation applied only to hands or only to faces:
| Data Type | AER | HPSv3 |
|---|---|---|
| Hand | 0.305 | 10.435 |
| Face | 0.367 | 10.358 |
The model trained with hand-only degradation achieves a lower overall AER than the model trained with face-only degradation, while both maintain HPSv3 scores close to that of the base FLUX model. This suggests that the anatomical region targeted during data construction affects the resulting performance.
W3: HAF-Bench mainly relies on visual language models for automatic evaluation. Although it provides manual verification, further explanations are needed regarding the reliability and generalization ability of the evaluation results.
Evaluation Reliability
We now report standard deviations and task-specific human–VLM agreement with Cohen’s κ to better characterize the variability of our results and the judge’s reliability on FLUX outputs.
All evaluations use 500 prompts and 5 seeds. To better characterize the variability of the results, we now report the mean and standard deviation:
| Methods | AER | HPSv3 |
|---|---|---|
| FLUX | 0.417 0.011 | 10.307 0.224 |
| FLUX-ASAP-DPO | 0.293 0.003 | 9.680 0.163 |
| FLUX-ASAP (Ours) | 0.289 0.005 | 10.360 0.186 |
Compared with the FLUX base model, FLUX-ASAP achieves a lower anatomical error rate while maintaining a similar HPSv3 score. Compared with FLUX-ASAP-DPO, it achieves a similar AER and a higher HPSv3 score, indicating better image quality as measured by HPSv3.
We separate human–VLM agreement into absolute and pairwise judgments and report Cohen's to account for agreement expected by chance. The previously reported 82% agreement combined these two tasks on FLUX-generated images. The task-specific results are as follows:
| Task | Agreement | Cohen's |
|---|---|---|
| Absolute | 86.2% | 0.657 |
| Relative | 77.8% | 0.643 |
These results show agreement beyond chance for both tasks and support the use of the VLM as an evaluator on the assessed outputs.
We sincerely appreciate the reviewer’s constructive feedback and insightful suggestions. Below, we provide point-by-point responses.
Our Contribution
Our main contribution is synthetic localized preferences, and the main benefit of our objective is better anatomy quality while preserving the global image quality. We add a direct comparison with LocalDPO to better assess the contribution of our optimization objective.
The main contribution of this work is synthetic localized preferences, a data construction strategy that enables DPO-style alignment to improve anatomical correctness in human image generation. Our objective is designed to make effective use of these localized preference pairs. Specifically, we introduce a margin-bounded DPO variant to better balance anatomical correctness and overall image quality.
We acknowledge that both finite target margins and region-aware weighting build on existing ideas. The contribution of our objective is to adapt and combine these ideas for localized anatomical preferences in diffusion and flow models. The results in Table 4 show further improvements over using the IPO formulation alone. Existing region-aware alignment methods differ in their training objectives and input requirements, which affects how directly they can be applied to our task:
We therefore added a direct comparison with LocalDPO :
In this comparison, FLUX-ASAP achieves both a lower AER and a higher HPSv3 score than FLUX-LocalDPO. These results support the effectiveness of our margin-bounded objective in balancing anatomical correctness and image quality with a simpler formulation.