Related papers: Reversible data hiding with dual pixel-value-order…
Deep hiding, concealing secret information using Deep Neural Networks (DNNs), can significantly increase the embedding rate and improve the efficiency of secret sharing. Existing works mainly force on designing DNNs with higher embedding…
LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when the distribution of the test data significantly deviates…
In science and engineering, machine learning techniques are increasingly successful in physical systems modeling (predicting future states of physical systems). Effectively integrating PDE loss as a constraint of system transition can…
Differentiable rendering aims to compute the derivative of the image rendering function with respect to the rendering parameters. This paper presents a novel algorithm for 6-DoF pose estimation through gradient-based optimization using a…
Human pose estimation (HPE) is a key building block for developing AI-based context-aware systems inside the operating room (OR). The 24/7 use of images coming from cameras mounted on the OR ceiling can however raise concerns for privacy,…
Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the…
Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods…
Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large language and…
Segmentation of microscopy images constitutes an ill-posed inverse problem due to measurement noise, weak object boundaries, and limited labeled data. Although deep neural networks provide flexible nonparametric estimators, unconstrained…
Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view…
In fringe projection profilometry, the high-order harmonics information of non-sinusoidal fringes will lead to errors in the phase estimation. In order to solve this problem, a point-wise posterior phase estimation (PWPPE) method based on…
This paper introduces HEPPO-GAE, an FPGA-based accelerator designed to optimize the Generalized Advantage Estimation (GAE) stage in Proximal Policy Optimization (PPO). Unlike previous approaches that focused on trajectory collection and…
We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…
Variational autoencoders (VAEs) have witnessed great success in performing the compression of image datasets. This success, made possible by the bits-back coding framework, has produced competitive compression performance across many…
Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…
The regression of 3D Human Pose and Shape (HPS) from an image is becoming increasingly accurate. This makes the results useful for downstream tasks like human action recognition or 3D graphics. Yet, no regressor is perfect, and accuracy can…
Infrared and visible image fusion integrates information from distinct spectral bands to enhance image quality by leveraging the strengths and mitigating the limitations of each modality. Existing approaches typically treat image fusion and…
Partial Differential Equation (PDE)-based approaches have gained significant attention in image despeckling due to their strong capability to preserve structural details while suppressing noise. However, conventional second-order PDE models…
Sequential Bayesian optimal experimental design (SBOED) for PDE-governed inverse problems is computationally challenging, especially for infinite-dimensional random field parameters. High-fidelity approaches require repeated forward and…
Traditional frequency based projection filters, or projection operators (PO), separate signal and noise through a series of transformations which remove frequencies where noise is present. However, this technique relies on a priori…