2025
FlexPainter: Flexible and Multi-View Consistent Texture Generation.
CoRR, June, 2025

ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback.
CoRR, May, 2025

RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification.
CoRR, March, 2025

TransPixeler: Advancing Text-to-Video Generation with Transparency.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
LucidFusion: Generating 3D Gaussians with Arbitrary Unposed Images.
CoRR, 2024

SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance.
CoRR, 2024

Motion Inversion for Video Customization.
CoRR, 2024

Denoising Diffusion Step-aware Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
Decompose and Realign: Tackling Condition Misalignment in Text-to-Image Diffusion Models.
CoRR, 2023

Not All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023