32 citations · 39 across the 15 of their papers we have counts for
18 papers
NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather
Yanying Li, Jinyang Li, Shengfeng He +3
We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs captured under diverse and mixed adverse weather conditions. Unli…
OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance
Zhaotong Yang, Yong Du, Shengfeng He +5
Image-based Virtual Try-On (VTON) concerns the synthesis of realistic person imagery through garment re-rendering under human pose and body constraints. In practice, however, exist…
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Xi Ye, Wenjia Yang, Yangyang Xu +4
Image-conditioned video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term tempo…
MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
Zhexin Zhang, Yangyang Xu, Yifeng Zhu +4
Recent advances in diffusion-based text-to-video models, particularly those built on the diffusion transformer architecture, have achieved remarkable progress in generating high-qu…
DeshadowMamba: Deshadowing as 1D Sequential Similarity
Zhaotong Yang, Yi Chen, Yanying Li +5
Recent deep models for image shadow removal often rely on attention-based architectures to capture long-range dependencies. However, their fixed attention patterns tend to mix illu…
Cross-Subject Mind Decoding from Inaccurate Representations
Yangyang Xu, Bangzhen Liu, Wenqi Shao +3
Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variabil…
HarmonPaint: Harmonized Training-Free Diffusion Inpainting
Ying Li, Xinzhe Li, Yong Du +3
Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and sty…
OmniVTON: Training-Free Universal Virtual Try-On
Zhaotong Yang, Yuhui Li, Shengfeng He +4
Image-based Virtual Try-On (VTON) techniques rely on either supervised in-shop approaches, which ensure high fidelity but struggle with cross-domain generalization, or unsupervised…
Stable Score Distillation
Haiming Zhu, Yangyang Xu, Chenshu Xu +5
Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing stren…
PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium
Xinzhe Li, Jiahui Zhan, Shengfeng He +4
Personalized image generation has made significant strides in adapting content to novel concepts. However, a persistent challenge remains: balancing the accurate reconstruction of…
Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing
Yangyang Xu, Wenqi Shao, Yong Du +4
Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities, yet balancing reconstruction fidelity and editability for real images re…
Zero-Shot Video Translation via Token Warping
Haiming Zhu, Yangyang Xu, Jun Yu +1
With the revolution of generative AI, video-related tasks have been widely studied. However, current state-of-the-art video models still lag behind image models in visual quality a…
DiffusionMat: Alpha Matting as Sequential Refinement Learning
Yangyang Xu, Shengfeng He, Wenqi Shao +3
In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conv…
RIGID: Recurrent GAN Inversion and Editing of Real Face Videos
Yangyang Xu, Shengfeng He, Kwan-Yee K. Wong +1
GAN inversion is indispensable for applying the powerful editability of GAN to real images. However, existing methods invert video frames individually often leading to undesired in…
Self-supervised Matting-specific Portrait Enhancement and Generation
Yangyang Xu Zeyang Zhou, Shengfeng He
We resolve the ill-posed alpha matting problem from a completely different perspective. Given an input portrait image, instead of estimating the corresponding alpha matte, we focus…
High-resolution Face Swapping via Latent Semantics Disentanglement
Yangyang Xu, Bailin Deng, Junle Wang +3
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to…
From Continuity to Editability: Inverting GANs with Consecutive Images
Yangyang Xu, Yong Du, Wenpeng Xiao +2
Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of…
Deep Texture-Aware Features for Camouflaged Object Detection
Jingjing Ren, Xiaowei Hu, Lei Zhu +5
Camouflaged object detection is a challenging task that aims to identify objects having similar texture to the surroundings. This paper presents to amplify the subtle texture diffe…