Publications

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

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

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

CVPR, 2022

We integrate a gradient estimation strategy into the gradient descent step of the Proximal Gradient Descent algorithm, driving it to deal with complex real-world image degradation.

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.

A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition

TCSVT, 2022

We model pedestrian attribute recognition as a multimodal problem and build a simple visual-textual baseline to captures the intra- and cross-modal correlations.