The paper introduces Implicit Bridge Consistency Distillation (IBCD), a method that enables single-step, bidirectional unpaired image translation without adversarial loss. IBCD uses a diffusion implicit bridge model that connects PF-ODE trajectories between distributions, parametrized on a signed time axis to select the target domain, allowing one network to translate in both directions in a single step. The authors also propose distribution matching for consistency distillation and an adaptive weighting scheme based on distillation difficulty, achieving state‑of‑the‑art performance on benchmark datasets and extending to brain MRI contrast translation.
arXiv:2608.22272v1 Announce Type: cross Abstract: Generative adversarial networks (GANs) can provide efficient image generation, while diffusion models offer high-quality image restoration but requir...
arXiv:2608. 06240v1 Announce Type: cross Abstract: Unpaired image-to-image translation must decide, per image, what to change and what to preserve without paired supervision.
arXiv:2607. 16294v1 Announce Type: cross Abstract: Paired image-to-image translation underpins a wide range of computer vision tasks, including image editing, sensor translation, and domain adaptation.
The paper introduces SMFSR, a one‑step real‑world super‑resolution framework that retains the noise‑started generation of diffusion models while conditioning on low‑resolution images. It uses LR‑conditioned SplitMeanFlow with Interval Splitting Consistency to collapse a multi‑step trajectory into a single average‑velocity prediction, and adds a GAN refinement stage with a DINOv3 discriminator and variational score distillation to enhance texture realism. Experiments show SMFSR achieves state‑of‑the‑art perceptual quality among one‑step diffusion‑based methods while maintaining fast inference.
arXiv:2608.29997v1 Announce Type: new Abstract: We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete dif...
Latent Diffusion-GAN (LD‑GAN) integrates adversarial learning into diffusion models by using the pretrained VAE as an energy‑based discriminator, avoiding extra parameters and preserving the latent priors. It introduces a structural consistency energy to align encoder and decoder features, improving perceptual quality. Experiments show LD‑GAN enhances sample fidelity, sharpness, and diversity across generation tasks while maintaining efficient training dynamics.
arXiv:2602.15396v2 Announce Type: replace Abstract: Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces in...
arXiv:2608.27885v1 Announce Type: new Abstract: Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not dire...
arXiv:2609.30988v1 Announce Type: new Abstract: Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while...
The paper introduces CM-RED, a fast MRI reconstruction method that combines a pretrained consistency model with the regularization by denoising framework. By integrating controlled noise injection into accelerated proximal gradient updates, CM-RED achieves high‑quality reconstructions on fastMRI knee and brain datasets with only four network function evaluations. It consistently outperforms existing diffusion‑ and consistency‑based approaches in quantitative metrics, visual fidelity, and robustness to hyperparameter changes.
ALADDIN is a one‑step face‑swapping method that distills a pre‑trained multi‑step diffusion model into a fast generator trained adversarially with identity and target‑preservation constraints. It offers a controllable trade‑off between identity transfer and attribute preservation via triplet pseudo‑label supervision, and it outperforms other one‑step methods in realism and target preservation while matching the best multi‑step model with far fewer evaluations and training pairs. The authors also uncover a bias in standard evaluation protocols and re‑evaluate baselines with an independent identity encoder.
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.