Ronghuan Wu portrait

Ronghuan Wu


, ,



I am a fourth-year PhD student in Computer Science at City University of Hong Kong, under the supervision of Jing Liao and Kede Ma. I am interested in making generative models more controllable and editable.

I interned at Adobe Research in summer 2026, working on image vectorization, and visited the University of Cambridge in summer 2025 to work with Rafal Mantiuk on HDR image and video generation. I received my B.S. from East China Normal University in 2022.


Projects

X2HDR: HDR Image Generation in a Perceptually Uniform Space

NeurIPS 2026 (Spotlight)

SemLayer teaser

SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons

CVPR 2026

LayerPeeler teaser

LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization

Ronghuan Wu, Wanchao Su, Jing Liao

SIGGRAPH Asia 2025

Chat2SVG teaser

Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models

Ronghuan Wu, Wanchao Su, Jing Liao

CVPR 2025

AniClipart teaser

AniClipart: Clipart Animation with Text-to-Video Priors

Ronghuan Wu, Wanchao Su, Kede Ma, Jing Liao

IJCV 2024

IconShop teaser

IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers

Ronghuan Wu, Wanchao Su, Kede Ma, Jing Liao

ACM TOG (SIGGRAPH Asia 2023)


Miscellaneous

I like to listen to the Stardew Valley OST. Occasionally, I play SuperBomb, which I started playing in 2007.

Friends at ECNU: Lingyang Zeng, Dingcui Yu

Dog animation