A survey on deep generative 3d-aware image synthesis

W Xia, JH Xue - ACM Computing Surveys, 2023 - dl.acm.org
Recent years have seen remarkable progress in deep learning powered visual content
creation. This includes deep generative 3D-aware image synthesis, which produces high …

Meta ControlNet: Enhancing Task Adaptation via Meta Learning

J Yang, J Zhao, P Wang, Z Wang, Y Liang - arXiv preprint arXiv …, 2023 - arxiv.org
Diffusion-based image synthesis has attracted extensive attention recently. In particular,
ControlNet that uses image-based prompts exhibits powerful capability in image tasks such …

Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering

X Wang, W Ma, A Wang, S Chen, A Kortylewski… - arXiv preprint arXiv …, 2024 - arxiv.org
For vision-language models (VLMs), understanding the dynamic properties of objects and
their interactions within 3D scenes from video is crucial for effective reasoning. In this work …

Meta ControlNet: Enhancing Task Adaptation via Meta Learning

VIAM LEARNING - openreview.net
Diffusion-based image synthesis has attracted extensive attention recently. In particular,
ControlNet that uses image-based prompts exhibits powerful capability in image tasks such …