Zhengyao Lv

CVPR'26

DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution

Zhengyao Lv, Menghan Xia, Xintao Wang, Kwan-Yee K. Wong

CVPR, 2026 Project Paper Code

A one-step video super-resolution framework integrating distribution-matching and adversarial supervision for efficient high-fidelity reconstruction.

ICCV'25

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

Zhengyao Lv*, Chenyang Si*, Tianlin Pan, Zhaoxi Chen, Kwan-Yee K. Wong, Yu Qiao, Ziwei Liu

ICCV, 2025 Project Paper Code

A consistency-distillation approach that decouples semantic and detail distillation, reducing video generation sampling steps while maintaining visual quality.

ICLR'25

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, Kwan-Yee K. Wong

ICLR, 2025 Project Paper Code

A training-free DiT sampling acceleration method achieving over 1.5× speedup, integrated into Diffusers and adapted to WAN 2.1.

Rethinking Cross-Modal Interaction teaser

ICCV'25

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

Zhengyao Lv*, Tianlin Pan*, Chenyang Si*, Zhaoxi Chen, Wangmeng Zuo, Ziwei Liu, Kwan-Yee K. Wong

ICCV, 2025 Project Paper Code

A parameter-efficient method that rebalances multimodal interactions to improve text-image alignment.

CVPR'24

PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis

Zhengyao Lv, Yuxiang Wei, Wangmeng Zuo, Kwan-Yee K. Wong

CVPR, 2024 Highlight Project Paper Code

A semantic image synthesis framework that adaptively combines layout and semantic features for improved layout alignment.

ECCV'24

ConceptExpress: Harnessing Diffusion Models for Single-Image Unsupervised Concept Extraction

Shaozhe Hao, Kai Han, Zhengyao Lv, Shihao Zhao, Kwan-Yee K. Wong

ECCV, 2024 Oral Project Paper Code

An unsupervised concept extraction method using pretrained diffusion models to locate, disentangle, and optimize concepts in images.

Semantic-Shape Adaptive Feature Modulation teaser

CVPR'22

Semantic-Shape Adaptive Feature Modulation for Semantic Image Synthesis

Zhengyao Lv, Xiaoming Li, Zhenxing Niu, Bing Cao, Wangmeng Zuo

CVPR, 2022 Paper Code

A shape-context-aware feature modulation method for realistic detail synthesis from semantic maps.

CVPR'21

Learning Semantic Person Image Generation by Region-Adaptive Normalization

Zhengyao Lv, Xiaoming Li, Xin Li, Fu Li, Tianwei Lin, Dongliang He, Wangmeng Zuo

CVPR, 2021 Paper Code

A two-stage framework for human pose transfer with semantic parsing prediction and region-adaptive normalization.

Zhengyao Lv - 吕峥瑶

Zhengyao Lv - 吕峥瑶

About Me

Education

Publications