Publications
![360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model](/media/360DVD.png)
360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model
arXiv
We propose a controllable panorama video generation pipeline named 360-Degree Video Diffusion model (360DVD) for generating panoramic videos based on the given prompts and motion conditions.
![NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results](/media/NTIRE2023.png)
NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results
CVPR Workshop, 2023
We develop a spatial-temporal two-stage model, wherein the first stage is a 4x image super-resolution network, and the second stage is a 4x video super-resolution network.
![Panoptic Compositional Feature Field for Editable Scene Rendering with Network-Inferred Labels via Metric Learning](/media/CVPR2023-PCFF.png)
Panoptic Compositional Feature Field for Editable Scene Rendering with Network-Inferred Labels via Metric Learning
CVPR, 2023
We introduce metric learing for leveraging 2D network-inferred labels to obtain discriminating feature fields, leading to 3D segmentation and editing results.
![Deep Generalized Unfolding Networks for Image Restoration](/media/CVPR2022-DGUNet.png)
![More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification](/media/ACMMM2022-MSDPA.png)
More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification
ACM MM, 2022
We introduce the multi-source knowledge ensemble in occluded re-ID to effective leverage external semantic cues learned from different domains.