Related papers: Reversible data hiding with dual pixel-value-order…

Reversible data hiding in encrypted domain(RDH-ED) can not only protect the privacy of 3D mesh models and embed additional data, but also recover original models and extract additional data losslessly. However, due to the insufficient use…

Virtual network embedding (VNE) is an crucial part of network virtualization (NV), which aims to map the virtual networks (VNs) to a shared substrate network (SN). With the emergence of various delay-sensitive applications, how to improve…

In this paper a general framework to adopt different predictors for reversible data hiding in the encrypted image is presented. We propose innovative predictors that contribute more significantly than conventional ones results in…

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced…

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where…

It is common in pose graph optimization (PGO) algorithms to assume that noise in the translations and rotations of relative pose measurements is uncorrelated. However, existing work shows that in practice these measurements can be highly…

This paper delves into the potential of DU-VIO, a dehazing-aided hybrid multi-rate multi-modal Visual-Inertial Odometry (VIO) estimation framework, designed to thrive in the challenging realm of extreme underwater environments. The…

Intra-frame prediction in the High Efficiency Video Coding (HEVC) standard can be empirically improved by applying sets of recursive two-dimensional filters to the predicted values. However, this approach does not allow (or complicates…

An accurate predictor is crucial for histogram-shifting (HS) based reversible data hiding methods. The embedding capacity is increased and the embedding distortion is decreased simultaneously if the predictor can generate accurate…

The variational autoencoder (VAE) is a simple and efficient generative artificial intelligence method for modeling complex probability distributions of various types of data, such as images and texts. However, it suffers some main…

H.264/Advanced Video Coding (AVC) is one of the most commonly used video compression standard currently. In this paper, we propose a Reversible Data Hiding (RDH) method based on H.264/AVC videos. In the proposed method, the macroblocks with…

We propose a three-stage 6 DoF object detection method called DPODv2 (Dense Pose Object Detector) that relies on dense correspondences. We combine a 2D object detector with a dense correspondence estimation network and a multi-view pose…

We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a…

In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial…

Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…

In reversible data embedding, to avoid overflow and underflow problem, before data embedding, boundary pixels are recorded as side information, which may be losslessly compressed. The existing algorithms often assume that a natural image…

Enhancing visual qualities of images plays very important roles in various vision and learning applications. In the past few years, both knowledge-driven maximum a posterior (MAP) with prior modelings and fully data-dependent convolutional…

Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no…