7 papers
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
Yansong Ning, Jingwen Ye, Zhongkai Wu +5
Constructing an interactive 3D open world from a user query is important. However, existing methods are primarily evaluated on idealized, simple queries, making it difficult to sys…
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
Youtan Yin, Yanning Zhou, Jiacheng Wei +6
Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region of interest for modification rathe…
FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization
Yikun Ma, Yiqing Li, Jingwen Ye +4
Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods either rely on manual parameter tun…
StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation
Yuze He, Yanning Zhou, Wang Zhao +4
We present StdGEN++, a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs. Existing 3D generative methods often…
Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
Lexiang Xiong, Chengyu Liu, Jingwen Ye +2
Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery…
CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modeling
Yuze He, Yanning Zhou, Wang Zhao +6
We present CHARM, a novel parametric representation and generative framework for anime hairstyle modeling. While traditional hair modeling methods focus on realistic hair using str…