5 papers
TextWand: A Unified Framework for Scene Text Editing
Shuyu Wang, Zhile Guan, Hongxiu Chen +5
We propose TextWand, a general-purpose framework that unifies scene text removal, generation, and replacement into a single model. By decomposing complex editing tasks into the ato…
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
Xu Jiang, Bin Chen, Gehui Li +3
The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agen…
InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception
Haijie Li, Yanmin Wu, Jiarui Meng +4
3D scene understanding has become an essential area of research with applications in autonomous driving, robotics, and augmented reality. Recently, 3D Gaussian Splatting (3DGS) has…
SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography
Xuanyu Zhang, Jiarui Meng, Zhipei Xu +4
3D Gaussian Splatting (3DGS) has emerged as a premier method for 3D representation due to its real-time rendering and high-quality outputs, underscoring the critical need to protec…
RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians
Qiankun Gao, Yanmin Wu, Chengxiang Wen +5
Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) h…