- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes CFIC, a generative image compression framework that aims to reduce model complexity while improving source-specific reconstruction quality at ultra-low bitrates. The method consists of three main components: asymmetric pruning of a pretrained one-step diffusion U-Net based on reconstruction sensitivity, Bit-Prior Coordination Modules (BPCM) that inject decoded multi-scale features into the generation process, and Latent Interface Steering (LIS) that preserves source information throughout the final image decoding stages.
Critical strengths
The main strength of this paper is its strong quantitative perceptual compression performance with a substantially reduced model size. The results on Kodak, DIV2K, and CLIC2020 show improvements in LPIPS and DISTS compared with several diffusion-based compression methods. The reduction from a large pretrained diffusion model to a 267M-parameter system is also meaningful.
Another positive aspect is the asymmetric pruning analysis. Table 3 provides a relatively convincing comparison against uniform pruning under similar parameter budgets and recovery training conditions. The asymmetric model retains reconstruction quality close to the unpruned model, suggesting that reconstruction sensitivity can be useful for allocating model capacity more effectively.
Critical weaknesses
My first concern is the limited methodological novelty and the insufficient validation of the claimed faithful reconstruction mechanism. The proposed BPCM and LIS modules mainly rely on multi-scale feature injection, cross-attention, residual connections, and trainable decoder adapters, which are closely related to existing conditioning and feature fusion techniques. Although Table 2 shows that removing these modules degrades performance, it does not establish whether the specific designs are necessary compared with simpler alternatives, such as direct feature addition, concatenation, or standard cross-attention with comparable parameters. Similarly, the so-called innovation residual in BPCM is constructed from two learned feature projections, but the paper does not clearly demonstrate that it actually captures source-specific information missing from the generative prior.
More importantly, I am not convinced by the qualitative results. In Appendix D (Figs. D.1–D.4), I find that CFIC's reconstructions look visually worse than those of AEIC-SE, particularly in local structures and fine details. The results do not show a convincing visual advantage for CFIC, despite the better aggregate perceptual metrics reported in the paper. Since "faithful decoding" and preservation of source-specific information are central claims, I consider this discrepancy important. I would expect stronger evidence that the proposed method actually preserves source content more faithfully, rather than only improving selected perceptual metrics.
My second concern is the practical efficiency and the limited comparison with recent lightweight generative compression methods. Although CFIC significantly reduces parameters and MACs compared with large diffusion-based codecs, the actual latency improvement over AEIC-SE is almost negligible: 285.9 ms versus 289.7 ms in Table 1, despite the much larger reduction in parameter count. This makes the practical efficiency advantage less convincing than the paper suggests.
Moreover, recent works such as CoD-Lite (Jia et al., ICML 2026) have specifically focused on lightweight and real-time generative image compression, reporting a much smaller model and fast encoding and decoding. Such methods are highly relevant to CFIC's compactness and efficiency claims, but are missing from the evaluation and discussion. I am not suggesting that their reported runtimes can be directly compared across different hardware and evaluation protocols. However, without considering these recent lightweight alternatives, it is difficult to judge how competitive CFIC really is in terms of the overall quality–complexity–latency trade-off.
In addition, the pruning sensitivity analysis is conducted on the small Set14 dataset, while the main pruning comparison in Table 3 is performed at 0.0549 bpp, outside the main ultra-low bitrate range emphasized in Fig. 4. It remains unclear whether the same capacity allocation is consistently optimal across different image contents and bitrate settings.
Questions for authors
-
Novelty of BPCM and LIS: What are the main technical advantages of BPCM and LIS over standard multi-scale conditioning or decoder feature injection? Have the authors considered simpler alternatives, such as direct feature fusion or standard cross-attention, under comparable parameter budgets? In particular, is there evidence that the proposed innovation residual captures information that is not already available in the generative features?
-
Qualitative reconstruction quality: In Appendix D (Figs. D.1–D.4), CFIC's reconstructions appear visually less convincing than AEIC-SE to me, despite the reported improvements in perceptual metrics. Could the authors explain this discrepancy? Are matched-bitrate visual comparisons or per-image fidelity measurements available to better support the claim of faithful decoding?
-
Practical efficiency and missing comparisons: CFIC reports substantially fewer parameters than AEIC-SE, but almost identical end-to-end latency (285.9 ms vs. 289.7 ms). What limits the actual speed improvement? Also, why are recent lightweight generative compression methods such as CoD-Lite (Jia et al., ICML 2026) not included or discussed? A comparison of the quality–complexity–latency trade-off would help clarify CFIC's practical advantages.
-
Generalization of the pruning strategy: The sensitivity analysis is performed on Set14, and Table 3 evaluates the pruning strategies at a single bitrate. Have the authors examined whether the stage-wise sensitivity ranking and the advantage of asymmetric pruning remain consistent across the main ultra-low bitrate range and different image contents?
4 comments
Thank you for the clarification and additional experiments. I appreciate the trainable four-channel entrance control, which strengthens the evidence for LIS, and the added RD comparison with CoD-Lite. However, my main concerns remain. The original latency is approximately 286 ms, and the additional measurements show only 6.83% and 3.87% time reductions under their respective settings. These gains are too modest to establish a meaningful practical speed advantage. CoD-Lite explicitly targets lightweight models and very fast decoding, which I consider a particularly promising direction for practical generative compression. Comparing RD performance without a corresponding latency comparison does not establish CFIC’s competitiveness in this trade-off. RDVQ is also an important missing baseline for evaluating reconstruction quality at a comparable model size. Furthermore, the image-level metrics do not resolve my concerns about local structural fidelity, and the response does not establish whether asymmetric pruning consistently outperforms uniform pruning across the main ultra-low-bitrate range. I therefore maintain my rating.
Thank you for your suggestion!
Our method is slower than CoD-Lite in encoding/decoding speed, but it significantly outperforms CoD-Lite on BD-Rate; we consider this a trade-off between speed and bitrate efficiency. For the experiments of CoD-Lite (additional), RDVQ and asymmetric pruning at ultra-low bitrates, we are conducting further experiments and will report the results.
Thank you for taking the time to respond to our comment, share your remaining concerns, and point out the experiments missing from our first response. Your feedback has helped us strengthen the study, and we have worked to address each concern below.
Latency and compactness. The end-to-end times below include encoding and decoding for 1024 × 1024 inputs on an RTX 4090.
| Method | Parameters | Latency (ms) | TMACs |
|---|---|---|---|
| CoD-Lite | 80M | 71.7 | 0.58 |
| RDVQ | 252M | 1134.9 | 4.19 |
| CFIC | 267M | 285.9 | 2.40 |
CoD-Lite offers the shortest coding time at 71.7 ms. CFIC takes 285.9 ms and uses fewer bits at matched PSNR, LPIPS, and DISTS across all three datasets in our earlier comparison. The DISTS BD-rate savings range from 48.65% to 74.01%. In this comparison, CFIC trades higher latency for better bitrate efficiency at a given reconstruction quality.
By “compact,” we mean that CFIC reduces the size of the pretrained one-step diffusion prior. We use reconstruction sensitivity to retain capacity in stages that matter most for reconstruction and prune less sensitive stages more aggressively. This reduces the full codec from 859M to 267M parameters, with reconstruction quality remaining close to the unpruned model at the operating point in Table 3.
RDVQ comparison. At a similar parameter count, CFIC has 74.8% lower end-to-end latency than RDVQ and the following BD-rates relative to RDVQ.
| Dataset | PSNR | MS-SSIM | LPIPS | DISTS | Patch-FID |
|---|---|---|---|---|---|
| Kodak | −48.26% | −15.38% | −28.10% | −5.49% | — |
| DIV2K | −37.00% | — | −39.94% | −39.96% | −54.00% |
| CLIC2020 | −33.30% | — | −41.43% | −44.33% | −71.17% |
Pruning at ultra-low bitrates. Across five operating points per variant (0.006–0.044 bpp), asymmetric pruning yields cubic BD-rates of −10.26% (PSNR), −17.61% (LPIPS), and −23.54% (DISTS) relative to uniform pruning. Below are original BD points:
| Pruning variant | BPP | PSNR (dB) ↑ | LPIPS ↓ | DISTS ↓ |
|---|---|---|---|---|
| Asymmetric Pruned (CFIC, Ours) | 0.00668 | 20.08 | 0.2908 | 0.1382 |
| Asymmetric Pruned (CFIC, Ours) | 0.01311 | 21.32 | 0.2173 | 0.1115 |
| Asymmetric Pruned (CFIC, Ours) | 0.02378 | 22.55 | 0.1616 | 0.0883 |
| Asymmetric Pruned (CFIC, Ours) | 0.03220 | 23.17 | 0.1370 | 0.0804 |
| Asymmetric Pruned (CFIC, Ours) | 0.04310 | 23.77 | 0.1191 | 0.0703 |
| Uniform Pruned | 0.00614 | 19.93 | 0.3224 | 0.1504 |
| Uniform Pruned | 0.01292 | 21.14 | 0.2381 | 0.1218 |
| Uniform Pruned | 0.02391 | 22.25 | 0.1788 | 0.0984 |
| Uniform Pruned | 0.03242 | 22.87 | 0.1509 | 0.0893 |
| Uniform Pruned | 0.04351 | 23.43 | 0.1353 | 0.0816 |
Local structural fidelity. We will use “source-conditioned reconstruction” in place of “faithful decoding” and tie our quality claims to the reported metrics.
Thank you!
Thank you for examining the pruning comparison and the details in the reconstruction crops. We added a trainable entrance control and measured total coding time under shared settings.
BPCM and LIS. BPCM routes decoded evidence during U-Net synthesis, and LIS keeps it accessible in later image-decoder layers. Both draw from the same coded representation. BPCM Direct keeps the projected difference E(e) − D(h) and bypasses attention. Its penalties support attention routing with this value construction, which is affine-equivalent to projecting the concatenated evidence and context. The trainable four-channel entrance still incurs a 25.40% DISTS BD-rate penalty, and removing hierarchical injection incurs a 21.92% penalty. These comparisons support the wide entrance and continued conditioning after the first projection.
Kodak BD-rate (%) relative to full CFIC
Local reconstruction quality. A lower image-level DISTS can coexist with less convincing detail in a crop. Figs. D.1–D.4 show the same crop regions at nearby, unequal rates. Fig. 5 reports image-level bpp and DISTS, and CFIC has lower values on both measures in each of the three examples shown. Fig. 4 reports the dataset-level RD results, and Fig. C.2 locates intermediate feature updates around structured regions.
Practical efficiency. At 1024 × 1024 on the RTX 4090, CFIC uses fewer parameters and MACs than AEIC-SE, with similar end-to-end latency. Runtime also depends on operator execution and coding overhead.
The new encoding-plus-decoding measurements use full-graph compilation, FP32 with TF32 enabled, and SDPA for both codecs. The U-Net uses tile size 128 with overlap 32. The VAE uses tile size 128 with halo 11. The second row tests a representative DIV2K/CLIC2020 resolution.
CoD-Lite. CoD-Lite has about 83M parameters and reports fast coding. We compare RD using five CFIC points and four CoD-Lite points per reported entry. CFIC's largest rate savings are on DISTS.
CFIC relative to CoD-Lite, cubic BD-rate (%)
Capacity allocation across bitrates. We use the Set14 sensitivity profile to guide topology selection, distill the selected topology once, and adapt the codec and reconstruction weights for each rate. Table 3 compares the two allocations at one Kodak operating point (0.0549 bpp). Asymmetric pruning preserves more reconstruction quality before recovery and retains its advantage afterward. Fig. 4 reports the RD performance of this shared topology after rate-specific adaptation on all three datasets.