相关论文: SHIFT: Stochastic Hidden-Trajectory Deflection for…

Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about which approach is generally preferable, and the substantial…

Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image…

We propose Diffusion-Sharpening, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories. Existing RL-based fine-tuning methods focus on single training timesteps and neglect trajectory-level alignment,…

Dexterous telemanipulation critically relies on the continuous and stable tracking of the human operator's commands to ensure robust operation. Vison-based tracking methods are widely used but have low stability due to anomalies such as…

While deep learning-based methods for blind face restoration have achieved unprecedented success, they still suffer from two major limitations. First, most of them deteriorate when facing complex degradations out of their training data.…

Flow watermarks efficiently link packet flows in a network in order to thwart various attacks such as stepping stones. We study the problem of designing good flow watermarks. Earlier flow watermarking schemes mostly considered substitution…

Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this…

In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile…

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…

Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering a promising perspective. However, due to the computational…

Digital contents have grown dramatically in recent years, leading to increased attention to copyright. Image watermarking has been considered one of the most popular methods for copyright protection. With the recent advancements in applying…

This paper studies the challenging task of makeup transfer, which aims to apply diverse makeup styles precisely and naturally to a given facial image. Due to the absence of paired data, current methods typically synthesize sub-optimal…

The rapid proliferation of realistic deepfakes has raised urgent concerns over their misuse, motivating the use of defensive watermarks in synthetic images for reliable detection and provenance tracking. However, this defense paradigm…

We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation-based method that explicitly models the discrepancy between…

Generative models transform random noise into images; their inversion aims to transform images back to structured noise for recovery and editing. This paper addresses two key tasks: (i) inversion and (ii) editing of a real image using…

Diffusion models are effective for waypoint prediction in visual navigation, but standard sampling and test time guidance can produce unreliable or inefficient trajectories when updates drift off the training manifold. We propose Fisher…

Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Leveraging the generalization power of diffusion models, we extend…

Mathematical methods of step-by-step and combined shifts are proposed for experimental data processing to reconstruct the measuring system impulse response distorted by shift-invariant blur. Proposed methods base on direct non-blind…

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

DNN watermarking is receiving an increasing attention as a suitable mean to protect the Intellectual Property Rights associated to DNN models. Several methods proposed so far are inspired to the popular Spread Spectrum (SS) paradigm…