Related papers: Free Lunch for Stabilizing Rectified Flow Inversio…
Pre-trained text-to-image (T2I) diffusion models have shown strong potential for real-world image super-resolution (Real-ISR), owing to their noise-started generation process that enables realistic texture synthesis and captures the…
By chaining a sequence of differentiable invertible transformations, normalizing flows (NF) provide an expressive method of posterior approximation, exact density evaluation, and sampling. The trend in normalizing flow literature has been…
Large-scale pre-trained diffusion models empower users to edit images through text guidance. However, existing methods often over-align with target prompts while inadequately preserving source image semantics. Such approaches generate…
Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scale fixed across the entire ODE trajectory. This is a fundamental mismatch: early steps are…
Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large-scale diffusion and flow matching models. However, such modern generative models suffer from…
Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…
We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant…
We introduce Random Projection Flows (RPFs), a principled framework for injective normalizing flows that leverages tools from random matrix theory and the geometry of random projections. RPFs employ random semi-orthogonal matrices, drawn…
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth…
We present UniRef-Image-Edit, a high-performance multi-modal generation system that unifies single-image editing and multi-image composition within a single framework. Existing diffusion-based editing methods often struggle to maintain…
Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter paradigm, combining a learned continuous motion latent space with a diffusion-based…
Recent works have demonstrated success in controlling sentence attributes ($e.g.$, sentiment) and structure ($e.g.$, syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for…
Multi-modal image fusion aims to consolidate complementary information from diverse source images into a unified representation. The fused image is expected to preserve fine details and maintain high visual fidelity. While diffusion models…
Though rectified flow models have achieved remarkable performance in image, video, and 3D generation, their practical deployments are challenged by slow inference speeds. Prior acceleration methods reuse cached features from previous steps,…
Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often…
Objective: This paper investigates how generative models, trained on ground-truth images, can be used \changes{as} priors for inverse problems, penalizing reconstructions far from images the generator can produce. The aim is that learned…
In this paper, we propose SRIF, a novel Semantic shape Registration framework based on diffusion-based Image morphing and Flow estimation. More concretely, given a pair of extrinsically aligned shapes, we first render them from multi-views,…
We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This…
Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently…
Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent…