- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper presents FidPoster to preserve fine-grained product details in poster generation, motivated by experiments showing that VAE compression degrades high-frequency information. PFA applies pixel-space fidelity supervision and jointly trains a reference-aware localizer; EVC uses this localizer and correspondence energy to correct sampling velocities without external masks. The authors also introduce FidPoster14K and FidPoster-Bench, achieving state-of-the-art results in automatic and human evaluations.
Critical strengths
- The paper is well-written and the overall idea is straight-forward.
- FidPoster-Bench has good efforts. It evaluates both paired fidelity and unpaired generalization.
Critical weaknesses
- The baseline may be unfair. All baselines are zero-shot, while FidPoster is fine-tuned on in-domain data. Plain LoRA SFT (Table 4: P-Text 82.09, SSIM 0.794) already beats every baseline in Table 2. The real gain of PFA+EVC over SFT is modest (+3.4 P-Text, +0.069 SSIM). SFT should appear in Table 2.
- A user study is necessary to assess the perceptual quality and overall effectiveness of the generated results.
- Comparisons with strong proprietary models, such as GPT Image 2, could provide a more meaningful assessment of the proposed method's performance.
Questions for authors
Please refer to weakness part.
4 comments
Response to reviewer 2A3x
W2: Human Evaluation of Perceptual Quality and Overall Effectiveness
A systematic human evaluation has already been conducted in Table 3 of the main paper. We evaluate 200 Independent Reference product samples across four dimensions: Product Fidelity, Layout & Composition, Visual Quality, and Commercial Usability. These dimensions assess the consistency between generated products and reference images, the visual presentation of the posters, and their practical applicability. The existing human evaluation results are as follows:
| Method | Product Fidelity ↑ | Layout & Composition ↑ | Visual Quality ↑ | Commercial Usability ↑ | Overall ↑ |
|---|---|---|---|---|---|
| BAGEL | 2.789 | 1.569 | 1.629 | 1.372 | 1.840 |
| FLUX.2 | 4.044 | 2.550 | 2.433 | 1.981 | 2.752 |
| IC-Custom | 3.773 | 2.259 | 2.271 | 1.844 | 2.537 |
| OmniGen2 | 2.283 | 1.307 | 1.437 | 1.275 | 1.576 |
| PosterOmni | 3.920 | 3.785 | 3.631 | 3.354 | 3.673 |
| Qwen-Image-Edit-2509 | 4.643 | 4.111 | 4.009 | 3.895 | 4.165 |
| Step1X-Edit | 4.461 | 1.554 | 1.559 | 1.450 | 2.256 |
| FidPoster (Ours) | 4.838 | 4.326 | 4.244 | 4.235 | 4.411 |
To further address the reviewer’s concerns regarding Perceptual Quality and Overall Effectiveness, we additionally introduce these two independent human evaluation dimensions based on the original evaluation. Perceptual Quality primarily measures the overall perceptual quality of generated posters, including visual naturalness, detail presentation, and generation artifacts. Overall Effectiveness comprehensively considers product presentation, visual appearance, and the fulfillment of design objectives to evaluate the overall effectiveness of the generated posters.
Considering the workload associated with human evaluation, we select three representative comparison methods: Qwen-Image-Edit-2509, PosterOmni, and Step1X-Edit. Among them, Qwen-Image-Edit-2509 is the base model adopted by FidPoster, PosterOmni is a representative method specifically designed for product poster generation, and Step1X-Edit is an image editing model that performs well in automatic product detail evaluation. These three methods provide comparisons from the perspectives of the base model, specialized poster generation methods, and image editing methods, respectively.
The results of the newly added Perceptual Quality and Overall Effectiveness evaluations are presented below:
| Method | Perceptual Quality ↑ | Overall Effectiveness ↑ |
|---|---|---|
| PosterOmni | 3.828 | 3.614 |
| Qwen-Image-Edit-2509 | 4.511 | 4.083 |
| Step1X-Edit | 3.565 | 2.367 |
| FidPoster (Ours) | 4.731 | 4.356 |
Among the three selected baselines, FidPoster achieves the highest scores in both Perceptual Quality and Overall Effectiveness. Specifically, FidPoster achieves a Perceptual Quality score of 4.731, outperforming Qwen-Image-Edit-2509 and PosterOmni by 0.220 and 0.903, respectively. Its Overall Effectiveness score reaches 4.356, exceeding the two methods by 0.273 and 0.742, respectively. These results demonstrate that FidPoster not only improves the fidelity of fine-grained product features, such as packaging text, logos, colors, and local textures, but also maintains good overall perceptual quality and complete poster generation performance.
Response to reviewer 2A3x
W3: Comparison with the Strong Closed-Source Model GPT-Image-2
Considering the relatively high inference cost of GPT-Image-2 and the workload associated with human evaluation, we conduct an additional comparison on the 200 Independent Reference samples in FidPoster-Bench, selecting two representative human evaluation dimensions: Product Fidelity, which measures the fine-grained product fidelity that is the primary focus of this work, and Perceptual Quality, which evaluates the overall visual perceptual quality of generated posters.
| Method | Product Fidelity ↑ | Perceptual Quality ↑ |
|---|---|---|
| GPT-Image-2 | 4.746 | 4.749 |
| FidPoster (Ours) | 4.838 | 4.731 |
The results show that although FidPoster is built upon the open-source Qwen-Image-Edit model, it achieves performance comparable to GPT-Image-2 on both evaluation dimensions. In terms of Perceptual Quality, FidPoster obtains a score of 4.731, only 0.018 lower than GPT-Image-2's score of 4.749. On Product Fidelity, the primary focus of this work, FidPoster achieves 4.838, exceeding GPT-Image-2's score of 4.746.
It is worth emphasizing that this work primarily focuses on accurately preserving fine-grained product information, including packaging text, logos, textures, and colors, rather than comprehensively optimizing the aesthetic quality and creative design of posters. We also observe that GPT-Image-2 occasionally regenerates product packaging text or local patterns into content that differs from the reference product in some generated results. Representative examples are provided in Appendix E.7 (Figure 13). These results demonstrate that FidPoster achieves perceptual quality close to that of a strong closed-source model while obtaining a higher score on the fine-grained product fidelity task targeted by this work, highlighting the practical value of the proposed fidelity-specific mechanisms.
Follow-up on Our Rebuttal
Dear Reviewer 2A3x,
Thank you once again for your valuable comments. As the discussion phase is approaching its end, we would like to kindly ask whether our clarifications and additional experiments have sufficiently addressed your concerns. We would be happy to provide further clarification if needed.
Thank you for your time and consideration.
Response to reviewer 2A3x
We have revised Table 2 in the main paper to directly include the results of Standard SFT and PFA-only, and adjusted the original description of Improvement accordingly. The revised Table 2 clearly distinguishes between two types of comparisons: the overall performance comparison of existing methods under zero-shot settings, and the controlled comparison of Standard SFT, PFA, and EVC using the same Qwen-Image-Edit backbone and training data. Tables 4–5 further analyze the contributions of individual fidelity components.
To further distinguish the gains from PFA and Standard SFT, we investigate whether these improvements transfer to product images from independent sources. To this end, we supplement the Independent Reference evaluation set with human evaluations of Standard SFT and PFA-only. The results are shown below:
On the Product Fidelity metric, which is the primary focus of this work, Standard SFT achieves a score of 4.677. Introducing PFA increases the score to 4.770, and further enabling EVC raises it to 4.838. This demonstrates that both PFA and EVC improve product detail preservation beyond standard SFT, even on the Independent Reference evaluation set, which contains no paired target posters.
Combined with the controlled automatic evaluation in Table 2 and the newly added human evaluation on Independent Reference, these results allow us to more clearly distinguish the contributions of each stage: standard SFT improves the model's basic product generation capability, PFA further enhances product detail preservation through decoded pixel-space supervision, and EVC provides additional reference-aware fidelity correction during inference. These results demonstrate that the product fidelity gains of the complete FidPoster method cannot be attributed solely to standard SFT.