- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes VPBrandLoop to preserve scene structure and brand identity for advertising image generation. A precomputed dominant vanishing point, perspective attributes, product and logo references are input into latent diffusion models through multi-scale geometric residuals and visual tokens. Then the authors use a line-segment detector and RANSAC to get geometric feedback and do sampling.
Critical strengths
- The paper focuses on a critical research problem. The geometric consistency of advertising image generation has been neglected in most previous works.
- The paper compares multiple baselines, although some of them are outdated.
Critical weaknesses
- The generation quality is not good in Figure 2. It seems that the proposed VPBrandLoop cannot generate some images with correct geometric relationships. The cans look like they are directly pasted onto the backgrounds.
- The authors only provide a few visual examples and there is no human study. So it is unclear whether the generation quality is good.
- The Brand Accuracy is 100 in Table 1 but 27 in Table 2. Although these results are from different subsets, the gap is so large.
- Removing "input VP Injection" even improves the SCPR in Table 2.
- The proposed method is like a combination of existing methods.
Questions for authors
- Please see the Weaknesses.
- Could the authors provide more visualization examples?
- Could the authors compare the proposed method with a simple Best-of-N baseline?