Publications (16)
GeoDiff3D: Self-Supervised 3D Scene Generation with Geometry-Constrained 2D Diffusion Guidance
Haozhi Zhu, Miaomiao Zhao, Dingyao Liu +4
3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further incr…
DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assembly
Fenggen Yu, Yiming Qian, Xu Zhang +4
We present a differentiable rendering framework to learn structured 3D abstractions in the form of primitive assemblies from sparse RGB images capturing a 3D object. By leveraging…
Semi-Supervised Co-Analysis of 3D Shape Styles from Projected Lines
Fenggen Yu, Yan Zhang, Kai Xu +2
We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines, achieving style patch localization with only weak supervision. Given a co…
DCSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
Fenggen Yu, Qimin Chen, Maham Tanveer +2
We present DCSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) r…
PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images
Ruiqi Wang, Yiming Qian, Fenggen Yu +4
Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints, requiring methods to handle significant pose variations. Existing appr…
Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images
Ruiqi Wang, Akshay Gadi Patil, Fenggen Yu +1
We introduce the first active learning (AL) model for high-accuracy instance segmentation of moveable parts from RGB images of real indoor scenes. Specifically, our goal is to obta…