Dongting Hu
YOU?
Author Swipe
View article: OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion Open
Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they s…
View article: AniFaceDiff: Animating stylized avatars via parametric conditioned diffusion models
AniFaceDiff: Animating stylized avatars via parametric conditioned diffusion models Open
View article: MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Input
MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Input Open
Recent advancements in Virtual Try-On (VITON) have significantly improved image realism and garment detail preservation, driven by powerful text-to-image (T2I) diffusion models. However, existing methods often rely on user-provided masks, …
View article: Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching
Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching Open
View article: Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching
Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching Open
Stereo matching plays a crucial role in various applications, where understanding uncertainty can enhance both safety and reliability. Despite this, the estimation and analysis of uncertainty in stereo matching have been largely overlooked…
View article: SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training Open
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely …
View article: AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models
AniFaceDiff: Animating Stylized Avatars via Parametric Conditioned Diffusion Models Open
Animating stylized avatars with dynamic poses and expressions has attracted increasing attention for its broad range of applications. Previous research has made significant progress by training controllable generative models to synthesize …
View article: A High Precison Phase Extraction Algorithm from a Single Shot Interferogram
A High Precison Phase Extraction Algorithm from a Single Shot Interferogram Open
Phase shifting interferometry is an optical metrology with a high precision, but it usually requires the expensive high precision phase shifter. Therefore, low cost methods of extracting phase from a single shot interferogram were very val…
View article: Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering Open
The rendering scheme in neural radiance field (NeRF) is effective in rendering a pixel by casting a ray into the scene. However, NeRF yields blurred rendering results when the training images are captured at non-uniform scales, and produce…
View article: DualFlow: Generating imperceptible adversarial examples by flow field and normalize flow-based model
DualFlow: Generating imperceptible adversarial examples by flow field and normalize flow-based model Open
Recent adversarial attack research reveals the vulnerability of learning-based deep learning models (DNN) against well-designed perturbations. However, most existing attack methods have inherent limitations in image quality as they rely on…
View article: A Simple Phase Retrieval Algorithm from a Single Shot Interferogram
A Simple Phase Retrieval Algorithm from a Single Shot Interferogram Open
Traditional phase-shifting interferometry technique cannot be used to measure time-varying phase distributions. But single shot techniques could resolve the problem. Many efforts have been made on the phase retrieval methods from a single …
View article: Improving Shape Retrieval by Integrating AIR and Modified Mutual<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mi>k</mml:mi></mml:mrow></mml:math>NN Graph
Improving Shape Retrieval by Integrating AIR and Modified MutualNN Graph Open
In computer vision, image retrieval remained a significant problem and recent resurgent of image retrieval also relies on other postprocessing methods to improve the accuracy instead of solely relying on good feature representation. Our me…