Related papers: FlowBypass: Rectified Flow Trajectory Bypass for T…
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both training and…
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model…
Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…
Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow,…
The Reflow operation aims to straighten the inference trajectories of the rectified flow during training by constructing deterministic couplings between noises and images, thereby improving the quality of generated images in single-step or…
In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios,…
Solving inverse problems without any training involves using a pretrained generative model and making appropriate modifications to the generation process to avoid finetuning of the generative model. While recent methods have explored the…
Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of…
Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted into an editable…
We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework, which is structured as a few-step editing process that preserves critical content while following closely to textual instructions.…
Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest,…
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under…
Flow matching as a paradigm of generative model achieves notable success across various domains. However, existing methods use either multi-round training or knowledge within minibatches, posing challenges in finding a favorable coupling…
Image fusion is a fundamental and important task in computer vision, aiming to combine complementary information from different modalities to fuse images. In recent years, diffusion models have made significant developments in the field of…
Generative modeling techniques such as Diffusion and Flow Matching have achieved significant successes in generating designable and diverse protein backbones. However, many current models are computationally expensive, requiring hundreds or…
In image editing, it is essential to incorporate a context image to convey the user's precise requirements, such as subject appearance or image style. Existing training-based visual context-aware editing methods incur data collection effort…
Training-free video object editing aims to achieve precise object-level manipulation, including object insertion, swapping, and deletion. However, it faces significant challenges in maintaining fidelity and temporal consistency. Existing…
Recent advancements in diffusion models have significantly broadened the possibilities for editing images of real-world objects. However, performing non-rigid transformations, such as changing the pose of objects or image-based…
Classifier-free guidance (CFG) is the workhorse for steering large diffusion models toward text-conditioned targets, yet its native application to rectified flow (RF) based models provokes severe off-manifold drift, yielding visual…
Fast flow models accelerate the iterative sampling process by learning to directly predict ODE path integrals, enabling one-step or few-step generation. However, we argue that current fast-flow training paradigms suffer from two fundamental…