Qian Wang (王茜)
ID Photo

I am a master student at the School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, advised by Prof. Jian Zhang. I received the B.E. degree from the College of Computer Science, Sichuan University, in 2022.

My research interest includes image restoration, image/video generation and image/video editing.

Publications

Prompt2Poster: Automatically Artistic Chinese Poster Creation from Prompt Only

Prompt2Poster: Automatically Artistic Chinese Poster Creation from Prompt Only

ACM MM, 2024

We propose an automatic poster creation framework, utilizing the capacity of LLM to extract user intention from prompts and generating the aligned background.

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model

CVPR, 2024

We propose a controllable panorama video generation pipeline named 360DVD for generating panoramic videos based on the prompts and motion conditions.

NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results

NTIRE 2023 Challenge on 360deg Omnidirectional Image and Video Super-Resolution: Datasets, Methods and Results

Mingdeng Cao, et al., Qian Wang, et al., Bingchun Luo

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

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

Deep Generalized Unfolding Networks for Image Restoration

Chong Mou, Qian Wang, Jian Zhang

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

More is better: Multi-source Dynamic Parsing Attention for Occluded Person Re-identification

Xinhua Cheng*, Mengxi Jia*, Qian Wang, Jian Zhang (* equal contribution)

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

A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition

Xinhua Cheng*, Mengxi Jia*, Qian Wang, Jian Zhang (* equal contribution)

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.