3 papers
cs.CV2026
View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity
Pufan Li, Bi'an Du, Shenghe Zheng +2
Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view images are rendered from a…
cs.CV2026
From Part to Whole: 3D Generative World Model with an Adaptive Structural Hierarchy
Bi'an Du, Daizong Liu, Pufan Li +1
Single-image 3D generation lies at the core of vision-to-graphics models in the real world. However, it remains a fundamental challenge to achieve reliable generalization across di…
cs.CV2025
Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image
Pufan Li, Bi'an Du, Wei Hu
Generating realistic 3D objects from single-view images requires natural appearance, 3D consistency, and the ability to capture multiple plausible interpretations of unseen regions…