- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper aims to speed up sampling in DBMs for image-to-image tasks. Existing consistency-based bridge methods, such as CDBM, are only learning the jump from an intermediate state straight to the clean image. Instead, this works proposes to train one model that can jump from any time t to any earlier time s along the bridge's probability-flow ODE. The experiments focus on 4x super-resolution and deblurring on ImageNet-512. The paper reports reports generally good results across this tasks.
Critical strengths
- The problem is well motivated
- Building the network around the exact bridge solution makes sense and the authors show that it trains much better than a plain average-velocity parameterization.
- The ablations are useful, covering the key components, that is parameterization, sign correction, full-flow vs. endpoint-only supervision, and flow composition. The finding that full-flow supervision helps even when sampling only ever targets s = 0 is interesting.
- The paper is clearly written and easy to follow
Critical weaknesses
-
While i like the idea itself, the novelty is slightly overstated, and the closest prior works are missing. For example, the paper says prior bridge-consistency models learn only the endpoint map (Fig. 2, introduction). That is not quite true as "Schrödinger Bridge Consistency Trajectory Models for Speech Enhancement"already learns a CTM-style map for arbitrary t -> s jumps along a Schrödinger-bridge ODE. In the same line, "Generalized Consistency Trajectory Models for Image Manipulation" learns arbitrary-time maps on a flow-matching ODE between two distributions. With paired data, this effectively becomes a deterministic bridge between degraded and clean images. Other bridge-consistency work are also missing, such as "Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation". The parameterization is also close to existing designs like "Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping".
-
The headline speedup is overstated. In Table 1, DBMSolver gets worse with more steps. Saying that BFM at 8 NFE matches DBMSolver at 20–30 NFE therefore compares against DBMSolver's weaker settings. It also looks to me that most of the improvement seem to come from the BFM pipeline versus the reproduced CDBM, not from learning the full flow.
-
It looks that all results are the authors' own reproduction. This means that none of these numbers can be compared with published work. Ideally the main comparison should focus on settings that match prior work conditions.
-
Following on the above, some of the reproduction appear weak. The CDBM flat across NFE (SR 3.00 / 2.96 / 3.01), whereas published CDBM improves with steps.
-
Unused standard benchmarks. The standard ImageNet-256 restoration suite from has published numbers for amny of these methods (I2SB, DDBM, DBIM, DBMSolver, etc). The paper even uses the I2SB 10k validation subset, but not these tasks.
-
Some baselines are missing, like one step image super-res methods "OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs", "Consistency Trajectory Matching for One-Step Generative Super-Resolution".
Questions for authors
Please see primarily the weaknesses section.
- Can the authors please report results on the standard I2SB ImageNet-256 tasks, against the published numbers of these methods?
- How exactly were CDBM and IBMD reproduced (training budget, learning rate, schedule tuning)? Why is the reproduced CDBM flat across NFE?
2 comments
Author response to 4Akk: Part 2/2
>> Published results and controlled reproductions (W3).
To clarify, not all comparisons are reproductions: Tab. 3 (E2H/DIODE; Tab. 2 in the original submission) uses the published CDBM, IBMD, DBIM and DBMSolver numbers, and 2-NFE BFM improves on the published 2-NFE results (e.g., on DIODE, BFM-2 achieves FID 1.69 versus 2.93 for published CBT-2 and 3.12 for IBMD-2).
For the ImageNet-512 comparison, we adapt the published CDBM and IBMD training procedures to the same task-specific DBM teachers and held-out evaluation set used by BFM, ensuring controlled comparisons rather than combining incompatible protocols. Our additional “standard” FID measurements (i.e., FID computed against original RGB images) confirm BFM's improvements over CDBM at 4 NFEs: 3.03 to 2.03 on SR4× and 2.97 to 2.49 on deblurring, and at 8 NFEs on deblurring (2.99 to 2.15).
Tab. 1 now reports standard FID alongside FID-VAE.
>> CDBM/IBMD reproduction and NFE behavior (W4/Q2).
Our CDBM reproduction follows the published training recipe with batch size 1024 and learning rate ; we select the best-performing evaluated CDBM checkpoint of 20k iterations for both tasks. We observed that the later 25k or 30k checkpoints showed worse FID-VAE, FID, and paired reconstruction metrics (e.g., at 25k, deblurring FID-VAE rises from 2.90 to 4.03 at 2 NFEs). For IBMD, we follow App. B of their paper: 3k student updates, learning rate , and five auxiliary updates per student update.
A nearly flat CDBM NFE curve is not itself evidence of an incorrect reproduction: as analyzed in AYF, endpoint-consistency errors can accumulate during repeated denoising and re-noising, so increasing NFEs need not improve quality monotonically. The CDBM, IBMD and BFM training and sampling settings are in App. G.3–G.4.
>> ImageNet-256 benchmarks and experimental protocol (W5/Q1) .
In response to the reviewer's ImageNet-256 request, we additionally evaluate BFM and CDBM on SR4× using both the I²SB 10k validation subset and the full 50k ImageNet validation set, with the same conditional DDBM teacher. I²SB's published ImageNet-256 results are not directly comparable, as they differ in bridge formulation, architecture, and evaluation protocol.
BFM consistently improves FID and LPIPS across both evaluation sets. On the full 50k validation set, BFM reduces standard FID from 9.92/9.75/9.58 to 7.08/6.80/6.71 at 2/4/8 NFEs, respectively. Notably, BFM-2 outperforms CDBM-8 in FID (7.08 versus 9.58).
ImageNet-256 SR4× standard FID↓ (I²SB 10k subset / full 50k validation; same DBM teacher):
| NFE | CDBM (10k) | BFM (10k) | CDBM (50k) | BFM (50k) |
|---|---|---|---|---|
| 2 | 12.86 | 10.00 | 9.92 | 7.08 |
| 4 | 12.67 | 9.78 | 9.75 | 6.80 |
| 8 | 12.51 | 9.66 | 9.58 | 6.71 |
>> Additional ImageNet-512 JPEG restoration benchmark (additional evidence).
We further evaluate BFM on ImageNet-512 JPEG-QF10 restoration using I²SB's corruption operator. All methods share the same task-specific EDM2-XS DBM teacher and the same 10k held-out ImageNet validation images.
ImageNet-512 JPEG-QF10 restoration (same 10k held-out images; sampling in App. G.4):
| Method | NFE | FID-VAE ↓ | FID ↓ | LPIPS ↓ | PSNR ↑ | SSIM ↑ |
|---|---|---|---|---|---|---|
| DBMSolver | 10 | 2.39 | 2.77 | 0.2458 | 25.11 | 0.7765 |
| DBMSolver | 20 | 2.30 | 2.51 | 0.2529 | 24.71 | 0.7578 |
| CDBM | 2 | 4.15 | 4.31 | 0.2765 | 24.36 | 0.7449 |
| IBMD-2 | 2 | 4.22 | 4.45 | 0.2708 | 24.63 | 0.7641 |
| BFM (Ours) | 2 | 3.67 | 4.05 | 0.2669 | 24.91 | 0.7646 |
| CDBM | 4 | 4.32 | 4.46 | 0.2825 | 24.17 | 0.7358 |
| BFM (Ours) | 4 | 2.34 | 2.54 | 0.2555 | 24.77 | 0.7576 |
| CDBM | 8 | 4.33 | 4.47 | 0.2831 | 24.16 | 0.7349 |
| BFM (Ours) | 8 | 2.32 | 2.50 | 0.2569 | 24.66 | 0.7539 |
>> Additional benchmarks (W6).
We now discuss OFTSR and CTMSR in Sec. 2.4 and App. K. Both target one-step super-resolution using different model formulations and evaluation protocols, whereas our controlled comparisons evaluate acceleration of the same conditional DDBM teacher. Their published scores therefore do not provide directly matched comparisons.
>> Solver comparisons (W2).
We agree that DBMSolver-10 is already competitive and have corrected the overly broad 20–30-NFE comparison. On the submitted ImageNet-512 tasks, BFM-8 achieves FID-VAE of 1.82/1.99 on SR4×/deblurring, versus DBMSolver-10's 1.71/2.00. On the new JPEG-QF10 task, BFM-4 achieves FID-VAE 2.34 against 2.39 for DBMSolver-10, while BFM-8 achieves FID 2.50, comparable to DBMSolver-20's 2.51. Moreover, at matched 4/8 NFEs, BFM is ahead of DBMSolver on all three tasks (4-NFE FID-VAE: 1.79/2.19/2.34 vs. 3.14/5.06/5.62; App. I.5).
We have corrected the solver comparison in the abstract, Sec. 4.2, contributions, and conclusion.
Author response to 4Akk: Part 1/2
We appreciate the reviewer's recognition that BFM is well motivated, that its bridge-structured parameterization is effective, and that the full-flow supervision ablation is interesting. We clarify the novelty and evidence below and report two new benchmarks (ImageNet-256 SR4×, ImageNet-512 JPEG-QF10).
>> Novelty and relation to prior flow models (W1).
We agree that Schrödinger Bridge Consistency Trajectory Models (SBCTMs) already learn arbitrary t→s Schrödinger-bridge transitions, and have corrected this statement in the introduction and Fig. 2. However, learning an arbitrary-time map is not, by itself, our claimed contribution. BFM develops a continuous-time consistency training formulation for the full conditional DDBM Bridge PF-ODE flow, using its analytic finite-time structure. We derive an analytic finite-time representation that separates the contributions of the current bridge state xt and conditioning endpoint xT from the learned interval-denoising quantity Dθ (Eq. 6):
fθ(xt,t,s,xT)=m(t,s)xt+n(t,s)xT+o(t,s)Dθ(xt,t,s,xT).
SBCTM learns Schrödinger-bridge trajectories through teacher-trajectory supervision in discrete-time, whereas BFM learns the conditional Bridge PF-ODE flow directly through a continuous-time objective. GCTM learns arbitrary-time maps on a flow-matching ODE; with paired data this is indeed a deterministic bridge, as the reviewer notes. The difference is that GCTM uses a generic flow-map parameterization with discrete-time training, whereas BFM reuses a pretrained DDBM, builds its exact finite-time coefficients into the map, and trains in continuous time.
TCD develops a semilinear interval representation for ordinary (noise-to-image) diffusion but does not consider conditional diffusion bridges, while IBCD focuses on single-step unpaired translation.
To the best of our knowledge, none of these works combines a continuous-time full-flow consistency objective with an analytic finite-time parameterization of the conditional DDBM Bridge PF-ODE.
We now cite SBCTM and TCD (Sec. 2.4) and IBCD (Sec. 2.3), and state the distinction in Sec. 2.4, and compare all of these methods in App. K.
>> Practical importance of the bridge-specific parameterization (W1).
We further investigate a generic average-velocity (AV) adaptation: our converted-AV baseline analytically converts the pretrained DBM denoiser while preserving its instantaneous Bridge PF-ODE velocity at initialization. We use the same backbone, training budget, and corresponding inference schedules and NFE budgets, with the appropriate parameterization-specific training factors. Despite this improved initialization, at 8 NFEs, converted AV achieves FID-VAE 8.45, compared with 1.99 for BFM. The corresponding FIDs are 8.60 and 2.15, respectively.
These results provide direct experimental evidence that BFM's bridge-structured formulation offers substantial practical advantages over the two tested generic flow-map adaptations.
>> The importance of full-flow learning is directly measured (W2).
The reviewer questions whether BFM's gains arise from full-flow learning or other differences in the training pipeline. Our controlled destination-supervision ablation in the submitted appendix directly isolates this effect: the full-flow and endpoint-directed variants share the same architecture, DBM initialization, training budget, and inference procedure, differing only in destination-time supervision.
Importantly, both models use s=0 endpoint-directed flow-map calls during inference. Nevertheless, full-flow training improves deblurring FID-VAE from 5.84 to 4.06 at 2 NFE, 2.97 to 2.19 at 4 NFE, and 2.16 to 1.99 at 8 NFE. This directly establishes the practical benefit of full-flow supervision independently of the shared training pipeline.