9 papers
Totem: Object-Centric 3D Memory for World-Consistent Video Generation
Zichen Wan, Tianyu Huang, Fan Li +3
Generating coherent videos grounded in a unified underlying world remains a major challenge, particularly under large viewpoint changes, where existing methods often struggle to ma…
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
Zehao Wang, Guanglei Yang, Yihan Zeng +4
Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data loc…
Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
Zihao Wang, Yuxiang Wei, Xinpeng Zhou +5
Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on multimodal large language model…
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
Haoze Zhang, Tianyu Huang, Zichen Wan +4
While recent video generation models have achieved significant visual fidelity, they often suffer from the lack of explicit physical controllability and plausibility. To address th…
Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision
Heming Xu, Xiaohui Liu, Zhilu Zhang +3
Real-world image de-weathering aims at removingvarious undesirable weather-related artifacts, e.g., rain, snow,and fog. To this end, acquiring ideal training pairs is crucial.Exist…
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity
Jingbo Lin, Zhilu Zhang, Wenbo Li +4
Recently, considerable progress has been made in all-in-one image restoration. Generally, existing methods can be degradation-agnostic or degradation-aware. However, the former are…
VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models
Kailai Feng, Yabo Zhang, Haodong Yu +4
Artistic typography is a technique to visualize the meaning of input character in an imaginable and readable manner. With powerful text-to-image diffusion models, existing methods…
Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations
Zhilu Zhang, Ruohao Wang, Hongzhi Zhang +1
In this paper, we consider two challenging issues in reference-based super-resolution (RefSR) for smartphone, (i) how to choose a proper reference image, and (ii) how to learn RefS…
MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation
Yuxiang Wei, Zhilong Ji, Jinfeng Bai +3
Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by…