19 citations · 32 across the 12 of their papers we have counts for
8 papers · 1 filter
RECAP-Forcing: Retaining Content Appearances for Long Video Generation
Haiyang Xu, Zheng Ding, Zhuowen Tu
Long autoregressive video generation faces a fundamental memory challenge: with a finite attention window, a model must decide which information from an ever-expanding history to r…
Explorative Inbetweening of Time and Space
Haiwen Feng, Zheng Ding, Zhihao Xia +4
We introduce bounded generation as a generalized task to control video generation to synthesize arbitrary camera and subject motion based only on a given start and end frame. Our o…
HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data
Mengqi Zhang, Yang Fu, Zheng Ding +3
3D hand-object interaction data is scarce due to the hardware constraints in scaling up the data collection process. In this paper, we propose HOIDiffusion for generating realistic…
Restoration by Generation with Constrained Priors
Zheng Ding, Xuaner Zhang, Zhuowen Tu +1
The inherent generative power of denoising diffusion models makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within…
Patched Denoising Diffusion Models For High-Resolution Image Synthesis
Zheng Ding, Mengqi Zhang, Jiajun Wu +1
We propose an effective denoising diffusion model for generating high-resolution images (e.g., 1024512), trained on small-size image patches (e.g., 6464). We name o…
DiffusionRig: Learning Personalized Priors for Facial Appearance Editing
Zheng Ding, Xuaner Zhang, Zhihao Xia +3
We address the problem of learning person-specific facial priors from a small number (e.g., 20) of portrait photos of the same person. This enables us to edit this specific person'…
Open-Vocabulary Universal Image Segmentation with MaskCLIP
Zheng Ding, Jieke Wang, Zhuowen Tu
In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background se…
Guided Variational Autoencoder for Disentanglement Learning
Zheng Ding, Yifan Xu, Weijian Xu +4
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement lear…