- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper introduces FLARE, a one-step generative codec that adds fidelity on top of a realism floor according to a continuous spatial fidelity-need field. Experiments show improved RPD performance in some reported settings.
Critical strengths
Addressing the distortion–perception (DP) trade-off under ultra low bitrate constraints in generative image compression, it is valuable to explore effective ROI-adaptive bitrate allocation strategies. This work employs an external human attention prediction model to identify regions requiring higher reconstruction fidelity and allocates more bits to these regions, thereby improving local reconstruction fidelity while maintaining global perceptual realism.
Critical weaknesses
- Although this paper focus on an interesting research topic, the proposed improvements are largely limited to spatially adaptive quantization within the AEIC-ME backbone. Compared with existing region-adaptive generative compression methods such as MRIDC and Relic, the architectural modifications are relatively limited.
- The experiments in the main text primarily focus on evaluating the effectiveness of FLaRE's fidelity-need field mechanism and presenting subjective evaluation results, while lacking key quantitative comparisons. Moreover, the existing qualitative analyses are limited to comparisons with AEIC-ME and OneDC, and the quantitative results in Figure 25 indicate that FLaRE does not demonstrate a clear advantage in global quality metrics.
- Appendix A.2 analyzes the per-channel bitrate distribution of the original AEIC-ME codec. However, this analysis does not provide sufficient evidence that retaining only the first 48 channels as the base group during FLaRE training and inference is sufficient to preserve a competitive realism floor at zero excess.
- This paper needs improvement in its writing and overall organization, as the presentation lacks sufficient logical structure and clarity. For example: (1) the "Our Contributions" section in the Introduction is overly verbose and lacks concise summarization; (2) The Introduction, Related Work, and Experiments sections frequently use semicolons to string together multiple ideas rather than presenting them in a logically structured manner; (3) In Sections 6.1 and 6.2, lengthy experimental descriptions are presented in single paragraphs without appropriate paragraph breaks, making them difficult to follow; (4) finally, many table and figure captions in the Appendix contain excessively detailed experimental descriptions, particularly Table 9 and Figures 24 and 25, which negatively affects readability.
- The main idea of spatial rate allocation for the RDP trade-off is very close to the `Wasserstein distortion' [1-3], which provides a standard evaluation paradigm or loss function construction. (For example, both extensive user studies and quantitative experiments are required; some standard evaluation protocols are preferred, such as CLIC with Elo scores. )
[1] Wasserstein distortion: Unifying fidelity and realism. [2] Good, cheap, and fast: Overfitted image compression with Wasserstein distortion [3] Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image Compression
Questions for authors
- Section 6.1 states that “Objective quality uses PSNR, LPIPS (Zhang et al., 2018), DISTS (Ding et al., 2022), and patch-FID over 256 × 256 crops. Baselines are the realism codecs AEIC-ME and OneDC (Xue et al., 2025), the generative codecs MS-ILLM (Muckley et al., 2023) and GLC (Jia et al., 2024), and the VVC intra anchor VTM (Bross et al., 2021)”, however, this claim is not well discussed in main text and connected to the corresponding results presented in Appendix Fig. 25. Moreover, Appendix G primarily discusses quantitative results on the 40-image subjective study set, without providing sufficient analysis of Fig. 25, making it difficult for readers to locate and understand these key quantitative evaluations. Given their importance, these results should be presented and discussed as part of the main experimental results rather than being relegated to the Appendix.
- The results in Fig. 25 indicate that FLaRE does not demonstrate an advantage over other methods. Why do the authors not provide further analysis of this observation? Additionally, why are reconstruction fidelity and perceptual realism not evaluated specifically within the regions indicated by the fidelity-need field in this comparison?
- The qualitative comparisons in the experimental section are limited to AEIC-ME and OneDC, which is insufficient. Given that Fig. 1 already includes comparisons with VTM, DiffC, DiT-IC, and PerCo, why are these methods not included in the qualitative comparisons in the main experiments? At least DiffC, DiT-IC, and PerCo (SD) have publicly available implementations.
- Fig. 5 uses three subfigures to validate Spatial Targeting, Monotonicity, and Effective Fidelity, respectively. Why not conduct these three related controlled experiments on the same image? Are the statistical curves on the right side of Fig. 5 based on the 40-image subjective study set? Moreover, the large-scale mechanism validation experiments are placed in the Appendix, while the caption of Fig. 5 does not explicitly specify that the statistical results are based on the 40-image set or adequately direct readers to Fig. 20 in the Appendix.
- FLaRE's inference efficiency advantage over MRIDC and Relic mainly stems from the one-step generation mechanism of its AEIC-ME backbone based on SD-Turbo. However, FLaRE does not offer an efficiency advantage over AEIC-ME itself. Moreover, generating the fidelity-need field relies on an external attention prediction model, which introduces additional computational overhead. According to Table 1, this process takes approximately 255 ms, nearly three times the codec's inference time. Although this overhead is reasonable, I suggest including it in FLaRE's overall inference cost rather than reporting it only in the footnote of Table 1. I also suggest moving the computational efficiency analysis to the Appendix, as computational efficiency is not a core advantage of FLaRE.
- The existing generative ROI compression methods discussed in the third part of Related Work, i.e., MRIDC and Relic, could be considered advances in rate–distortion–perception and generative compression. Moreover, the methods discussed in the region-adaptive coding part are relatively outdated. More recent works, such as C-ROI, TV-ROI, and Implicit Bit Allocation, should also be reviewed.
- Appendix A.2 aims to support a general conclusion that the 320-dimensional latent representation of AEIC-ME contains substantial redundancy, allowing 272 channels to be repurposed for a new information-coding task. However, the analysis demonstrates rate occupancy rather than representation redundancy in a strict sense. Moreover, the analysis is conducted only on Kodak, a very small dataset, and should be further validated across different image distributions, such as DIV2K and CLIC 2020. Additionally, the 48 channels in the analysis refer to the top 48 channels ranked by bitrate, whereas FLaRE appears to use a fixed partition of the first 48 channels as the base group during training and inference. This creates a logical gap that requires clarification. The authors should explain the relationship between the fixed channel partition and the offline rate-based ranking, and justify why the Top-48 rate concentration observed in AEIC-ME provides sufficient grounds for the channel split adopted in the retrained FLaRE model.
- Fig. 1 presents a qualitative comparison of different methods. The abbreviations of these baseline methods should be explicitly introduced in the Introduction or Related Work section, and the corresponding references should be included in the figure.
7 comments
Response to Reviewer nwHX (2/7)
Weakness 2 / Question 1 / Question 2 — too little quantitative comparison in the body, no advantage in the global metrics of Fig. 25 (now Fig. 28), no separate evaluation inside the field's region
We appreciate the request for clearer quantitative evidence, an explanation of Fig. 28 (Fig. 25 in the submission), and separate quality measurements within the selected region. We have expanded the region-level comparisons and reorganized Sec. 6 accordingly.
Why global metrics show limited gains. At the study operating points, FLaRE sends 29–43% of its payload to the field's active area, a small fraction of the image. This deliberately prioritizes regional fidelity over globally averaged quality. Relative to AEIC-ME on the study set, global LPIPS changes by +0.052 / +0.018 and PSNR by −0.54 / +0.39 dB; on CLIC and DIV2K, LPIPS changes by +0.004 to +0.016, with comparable or favorable PSNR and DISTS. Importantly, zero-excess FLaRE is comparable to AEIC-ME at matched rate, indicating that the global differences arise when excess bits are directed to selected regions. We therefore do not claim superiority on global metrics at equal total rate.
Requested region-level baseline comparison. Appendix Table 10 (Table 9 in the submission) already reported region PSNR/LPIPS and background quality on three datasets. We have added matched-rate region PSNR, LPIPS, and DISTS for every Sec. 6.1 baseline, including DiT-IC, VTM, MS-ILLM, and GLC (Table 17). FLaRE improves region PSNR by 2.3–6.2 dB over those baselines, with lower region LPIPS and DISTS (Table 17). We interpret this cautiously: global codecs are not designed to concentrate rate within the specified region, so this alone does not establish superiority among ROI methods.
Controlled comparison among ROI designs. MRIDC and Relic et al. address similar regional objectives at overlapping rates, but their code and checkpoints are unavailable (Appendix E). Our original submission therefore relied on matched-total-rate subjective and qualitative comparisons. To address the reviewer's concern more directly, we additionally trained four variants from the same pretrained model, with matched rate weight, sparse field, and region definition (Table nwHX-1): (i) the field in the training loss only; (ii) + the field as a codec input; (iii) + the channel split and its gate; (iv) + the training-only auxiliary decoder.
Table nwHX-1 — In-region quality of variants (i)–(iv) at a matched total rate and at a matched in-region rate (40 study images)
at the same total rate, 0.0611 bpp (Fig. 6)
| Design (model) | Total bpp | In-region bpp | Concentration | Region PSNR (dB) | Region LPIPS | Region DISTS | Region FID | Region HF (source = 1) |
|---|---|---|---|---|---|---|---|---|
| (i) field in the training loss only | 0.0611 | 0.0862 | 1.9 | 23.82 | 0.263 | 0.241 | 213.8 | 0.28 |
| (ii) + field as a codec input | 0.0611 | 0.3343 | 6.0 | 28.62 | 0.099 | 0.167 | 143.4 | 0.60 |
| (iii) + channel split and gate | 0.0611 | 1.0109 | 18.9 | 30.60 | 0.031 | 0.102 | 70.2 | 0.77 |
| (iv) + auxiliary decoder | 0.0611 | 1.0436 | 19.6 | 28.89 | 0.025 | 0.082 | 55.5 | 1.06 |
at the same in-region rate, 0.40 bpp (Fig. 32)
| Design (model) | Total bpp | In-region bpp | Concentration | Region PSNR (dB) | Region LPIPS | Region DISTS | Region FID | Region HF (source = 1) |
|---|---|---|---|---|---|---|---|---|
| (ii) + field as a codec input | 0.0651 | 0.4000 | 6.7 | 29.17 | 0.101 | 0.174 | 155.1 | 0.62 |
| (iii) + channel split and gate | 0.0404 | 0.4000 | 11.3 | 27.87 | 0.057 | 0.113 | 75.6 | 0.71 |
| (iv) + auxiliary decoder | 0.0393 | 0.4000 | 11.6 | 26.98 | 0.046 | 0.104 | 67.6 | 0.94 |
Concentration = the region's bit share ÷ its area share.
Response to Reviewer nwHX (3/7)
Weakness 2 / Question 1 / Question 2 — too little quantitative comparison in the body, no advantage in the global metrics of Fig. 25 (now Fig. 28), no separate evaluation inside the field's region (continued)
At 0.0611 total bpp, region FID improves 213.8 → 143.4 → 70.2 → 55.5, and DISTS 0.241 → 0.167 → 0.102 → 0.082. The split-and-gate step increases concentration from 6.0 to 18.9; at full field strength it holds background rate at 0.0236 → 0.0237 bpp, whereas (ii) raises it 0.0449 → 0.0524 bpp (Table nwHX-2). At a matched 0.40 in-region bpp, (ii) has higher region PSNR than (iv) (29.17 vs. 26.98 dB), but substantially worse FID (155.1 vs. 67.6). Variant (i) cannot reach that in-region-rate range even at its first nonzero strength; its relative high-frequency energy reaches only 0.32 (Figs. 6 and 32, both new in the revision). These comparisons identify the split and gate as the main source of spatially targeted allocation.
Table nwHX-2 — Bit allocation as the field strength a = η³ opens from 0 to 1 (40 study images)
| Design (model) | In-region bpp (η = 0 → 1) | Background bpp (η = 0 → 1) | Background change | Concentration |
|---|---|---|---|---|
| (i) field in the training loss only | 0.0710 / 0.1347 (no field input; two operating points) | 0.0416 / 0.0898 | – | 1.9 / 1.6 |
| (ii) + field as a codec input | 0.0494 → 0.4583 | 0.0449 → 0.0524 | +16.7 % | 7.3 |
| (iii) + channel split and gate | 0.0427 → 1.1006 | 0.0236 → 0.0237 | +0.4 % | 19.6 |
| (iv) + auxiliary decoder | 0.0414 → 1.0441 | 0.0226 → 0.0223 | −1.3 % | 19.6 |
Auxiliary supervision (Table nwHX-3). Relative to (iii), (iv) trades 1.7 dB of region PSNR (30.60 vs. 28.89 dB) for better LPIPS (0.031 → 0.025), DISTS (0.102 → 0.082), and high-frequency energy (0.77 → 1.06). Direct supervision's region FID worsens beyond its best field strength on all three datasets: 69.8 → 70.4 (study), 61.9 → 63.5 (DIV2K), and 24.9 → 28.0 (CLIC). Auxiliary supervision instead maintains perceptual improvement as region rate increases. Together, the controlled results separate where the bits go (split and gate) from how their added fidelity affects perceptual quality (auxiliary supervision). Full results appear in Sec. 6.3 (new in the revision) and Appendix I.
Table nwHX-3 — Region perceptual metrics for auxiliary versus direct output supervision as the field strength is raised; each cell is Aux / Direct
| Strength η | Study set (40) Region FID | Study set (40) Region DISTS | DIV2K validation (100) Region FID | DIV2K validation (100) Region DISTS | CLIC 2020 test (428) Region FID | CLIC 2020 test (428) Region DISTS |
|---|---|---|---|---|---|---|
| 0 (no field) | 102.5 / 100.4 | 0.155 / 0.156 | 88.7 / 87.1 | 0.168 / 0.168 | 35.6 / 34.1 | 0.155 / 0.155 |
| 0.2 | 68.8 / 76.7 | 0.109 / 0.116 | 61.9 / 65.8 | 0.115 / 0.121 | 24.3 / 25.3 | 0.106 / 0.111 |
| 0.4 | 64.4 / 72.0 | 0.091 / 0.101 | 49.9 / 61.9 | 0.095 / 0.107 | 20.1 / 24.9 | 0.089 / 0.099 |
| 0.6 | 57.8 / 69.8 | 0.086 / 0.100 | 46.8 / 62.0 ↑ | 0.089 / 0.104 | 18.8 / 26.0 ↑ | 0.082 / 0.098 |
| 0.8 | 55.6 / 70.3 ↑ | 0.083 / 0.102 ↑ | 45.4 / 63.0 ↑ | 0.085 / 0.105 ↑ | 18.2 / 27.3 ↑ | 0.078 / 0.100 ↑ |
| 1.0 | 55.5 / 70.4 ↑ | 0.082 / 0.101 | 45.0 / 63.5 ↑ | 0.084 / 0.105 | 17.9 / 28.0 ↑ | 0.076 / 0.100 ↑ |
↑ marks a value that worsened relative to the previous strength; it occurs only under direct supervision.
We have also reorganized the experimental section. Our experiments are three of different kinds — the controlled comparison between designs, the subjective study, and the comparison with existing codecs — so Sec. 6.1's setup is now split in three, each stating its purpose, its data and the basis on which rates are matched. The controlled comparison between designs is now a section of the body (6.3; the four variants above), and the comparison with existing codecs is a separate, final section of Sec. 6 (6.6) that points directly at Fig. 28 (Fig. 25 in the submission), the BD-rates and Appendix Table 10 (Table 9 in the submission). That section states that global metrics are insensitive to where bits land, that an in-region comparison favours region-adaptive codecs, and why we are not ahead in Fig. 28 (Fig. 25 in the submission), together with what the zero-excess curve means.
Response to Reviewer nwHX (1/7)
We sincerely thank the reviewer for this careful and insightful review. Please find our point-by-point response below.
Weakness 1 — the architectural modification is small compared with MRIDC / Relic et al.
We appreciate this observation: our change stays inside the AEIC-ME backbone and is a smaller structural modification than MRIDC's or Relic et al.'s. We respectfully suggest that achieving region control with a smaller architectural change can also be beneficial. Both methods obtain region control by changing how the decoder executes: MRIDC masks the VQ tokens outside the ROI and predicts them before iterative diffusion decoding, and Relic et al. transmit a spatial timestep map and vary quantization, entropy coding and iterative denoising according to it. FLaRE, by contrast, is a coding mechanism that turns an external continuous field into bit allocation inside a one-step realism codec (a non-transmitted field that gates and scales a dedicated message latent, with training-only auxiliary supervision). Because the change sits in the encoder-side coding rather than in the decoder's execution, no iterative sampler or decoding graph is altered for region control and decoding stays at one step (Table 14 (Table 1 in the submission): MRIDC 20 steps, Relic et al. 5–50 steps). The added cost over AEIC-ME is about +1M parameters and +17 ms of codec time, and because the field's effect is absorbed into the hyperlatent, no map is transmitted as side information, unlike Relic et al. (Appendix Table 15 (Table 12 in the submission)). We agree with Q5 that the DeepGaze inference time needed to produce the field (about 255 ms on Kodak) belongs in FLaRE's overall inference cost, and Table 14 (Table 1 in the submission) now reports it that way. That map-generation cost would be the same for MRIDC or Relic et al. if they took the same attention map, so for the structural comparison here we quote the codec-side numbers without it.
Whether the simplicity cost us performance. On the digitized Kodak curves of the two papers (Fig. 28 (Fig. 25 in the submission)), FLaRE is ahead on whole-image PSNR, LPIPS and DISTS at every reported point where the rates overlap — though with neither code nor checkpoints public this is not a fully matched comparison.
In summary, the novelty of this paper is not a new decoder architecture but the mechanism that turns a non-transmitted continuous field into bit allocation, and the measured properties of that mechanism (the control characteristics, the region fidelity gain at equal rate, the subjective study). We hope this clarifies why we view the compact architectural change as a meaningful aspect of the contribution.