- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes DECOR-VTON, a two-stage virtual try-on framework that leverages FLUX.1 Fill as its base model. To improve garment-to-person spatial correspondence, the first stage introduces probabilistic warp consistency, integrated into the late dual-stream attention blocks. Building on this learned correspondence, the second stage retrieves local high-resolution garment features and incorporates them into downstream single-stream blocks. The authors evaluate the proposed method on standard benchmarks (VITON-HD and DressCode) and provide ablation studies that validate the effectiveness of the supervision and feature retrieval modules.
Critical strengths
-
The coarse-to-fine retrieval architecture is highly intuitive and well-justified. Since spatial localization alone cannot restore fine-grained information lost in coarse garment tokens, the retrieval branch effectively supplies high-resolution reference features.
-
This method offers a practical and scalable source of self-supervision in the absence of ground-truth correspondence annotations, successfully mitigating reliance on external matching teachers or pseudo-labels.
Critical weaknesses
-
While the qualitative examples are compelling, the global metrics on the whole image fail to show how consistently the method preserves fine details—such as text, logos, or intricate repeated patterns—across the full test set. Specifically, in Table 2, Phase I substantially improves PCK from 0.885 to 0.980, yet global metrics like SSIM and LPIPS remain unchanged at the reported precision, leaving a gap between improved correspondence and tangible detail reproduction. Furthermore, the ablation study in Table 8 conflates spatial resolution with the VGG feature layer level, making it difficult to determine whether the observed performance gains stem directly from higher-resolution feature retrieval or from layer-specific semantic representation.
-
While the ablation study shows that combining both stages yields performance gains, it does not isolate the precise contribution of the proposed routing mechanism. For rigorous control, an experiment should freeze the garment features and injection modules and vary only the retrieved spatial regions. Without this baseline, it is unclear whether the improvements stem from accurate, correspondence-guided feature selection or merely from the capacity added by an extra feature branch. Additionally, the lack of a direct empirical comparison with CORAL—a closely related method highlighted in the related work—limits the assessment of the proposed correspondence supervision mechanism.
Questions for authors
-
Could the authors provide a targeted quantitative or qualitative evaluation focused on garments featuring text, logos, or complex repeated patterns? Additionally, to isolate the routing mechanism's efficacy, could you include a control experiment in which the retrieved regions are randomly shuffled or misaligned, while keeping the feature injection modules fixed? This would help clarify whether the detail fidelity stems from accurate correspondence-guided routing rather than simply increasing feature capacity.
-
Could the authors clarify the exact implementation details for computing PCK@16? Please clarify: 1) the selection criteria for evaluation keypoints and any pseudo-label filtering mechanisms applied; 2) the specific attention layers and diffusion timesteps used for feature extraction; 3) whether the person features are extracted from noisy ground-truth images or from generated intermediate samples. Furthermore, is a direct empirical comparison with CORAL supervision available under the same unified training setup?
7 comments
Official Author Responses to Reviewer xGD6 [2/7]
W1.1 + Q1.1: Detail Fidelity on Text, Logos, and Repeated Patterns
W1.1 The global metrics on the whole image fail to show how consistently the method preserves fine details—such as text, logos, or intricate repeated patterns—across the full test set. Specifically, in Table 2, Phase I substantially improves PCK from 0.885 to 0.980, yet global metrics like SSIM and LPIPS remain unchanged at the reported precision, leaving a gap between improved correspondence and tangible detail reproduction.
Q1.1 Could the authors provide a targeted quantitative or qualitative evaluation focused on garments featuring text, logos, or complex repeated patterns?
Unchanged SSIM and LPIPS. We thank the reviewer for this observation. We would like to emphasize that the discrepancy between correspondence accuracy and image reconstruction metrics in Table 2 is consistent with the central motivation of our two-phase framework. Our hypothesis is that improving garment–person correspondence alone is insufficient to fully preserve fine-grained garment details.
Fine-grained detail evaluation. To evaluate garment detail preservation, we automatically categorize all 2,032 VITON-HD test garments using Qwen3-VL-32B-Instruct into three overlapping groups: text/typography (1,140), logos/graphic prints (1,054), and complex repeated patterns (628). To avoid manual test-set selection, the categories are determined solely from reference garment images, independently of generated results. We then compute garment-masked spatial LPIPS between generated and ground-truth images and report the average scores for each category. DECOR-VTON achieves the lowest garment-region LPIPS across all three categories, with approximately 8.8%, 8.7%, and 7.7% relative reductions over DECOR-VTON (Baseline), respectively, based on the rounded scores. It also outperforms CORAL, Leffa, and OrthoTryOn across these subsets, providing quantitative evidence of improved garment fidelity on images containing fine-grained details (revised Appendix C.12, Table 17).
Table R5. Garment-masked spatial LPIPS (↓) on paired VITON-HD, stratified by automatically identified garment attributes. Best results are shown in bold.
| Method | Text (1,140) ↓ | Logos (1,054) ↓ | Patterns (628) ↓ |
|---|---|---|---|
| CORAL | 0.1420 | 0.1411 | 0.1600 |
| Leffa | 0.1463 | 0.1462 | 0.1662 |
| OrthoTryOn | 0.1969 | 0.1956 | 0.2154 |
| DECOR-VTON (Baseline) | 0.1448 | 0.1433 | 0.1629 |
| DECOR-VTON (Phase I only) | 0.1437 | 0.1426 | 0.1638 |
| DECOR-VTON (w/o Phase I) | 0.1396 | 0.1383 | 0.1577 |
| DECOR-VTON (Ours) | 0.1320 | 0.1308 | 0.1504 |
Key takeaway: On overlapping attribute subsets selected from all 2,032 VITON-HD test garments, DECOR-VTON achieves the lowest garment-masked LPIPS for text (0.1320), logos (0.1308), and complex patterns (0.1504), without selecting examples based on generated outputs.
Official Author Responses to Reviewer xGD6 [3/7]
W1.2: Separating VGG Feature Resolution from Abstraction
Furthermore, the ablation study in Table 8 conflates spatial resolution with the VGG feature layer level, making it difficult to determine whether the observed performance gains stem directly from higher-resolution feature retrieval or from layer-specific semantic representation.
Table R3. Controlled ablation of VGG feature abstraction levels at a fixed spatial resolution on VITON-HD (revised-paper Table 14). Best results are shown in bold.
| Method | FID (P/U) ↓ | KID (P/U) ↓ | SSIM ↑ | LPIPS ↓ | DISTS ↓ |
|---|---|---|---|---|---|
| VGG Block 1 (128 × 96) | 4.63 / 8.76 | 0.20 / 0.83 | 0.896 | 0.040 | 0.065 |
| VGG Block 2 (128 × 96) | 4.58 / 8.81 | 0.19 / 0.85 | 0.895 | 0.040 | 0.066 |
| VGG Block 3 (128 × 96) | 4.58 / 8.75 | 0.21 / 0.76 | 0.895 | 0.040 | 0.065 |
Effect of retrieval feature resolution and abstraction level. Table 8 evaluates features from different VGG blocks at spatial resolutions ranging from to . To further examine the effect of feature abstraction, we conduct a controlled experiment using VGG Blocks 1–3 at the same resolution of , with identical retrieval and injection settings (Table R3; revised-paper Table 14). VGG Block 3 achieves the lowest unpaired FID/KID (8.75/0.76) and a paired FID of 4.58, matching Block 2. The comparable results across blocks suggest that different feature abstraction levels can support effective retrieval at a fixed spatial resolution.
Key takeaway: Feature abstraction is evaluated at a fixed resolution: VGG Block 3 offers the best unpaired FID/KID, but overall performance remains comparable across Blocks 1–3.
Official Author Responses to Reviewer xGD6 [1/7]
We sincerely thank Reviewer xGD6 for recognizing the intuitive and well-justified coarse-to-fine retrieval architecture and its teacher-free correspondence supervision. We appreciate the requests for more direct evidence of fine-detail preservation and causal routing. Below, we address (1) automatically defined garment-attribute subsets drawn from the full test split, (2) a fixed-resolution VGG abstraction-level ablation, (3) shuffled-region routing with unchanged model weights, (4) the PCK evaluation protocol and stricter thresholds, and (5) controlled comparisons with CORAL. The revised paper includes these analyses in Tables 1–2 and 14–17 and Appendices B.6 and C.9–C.12.