2 papers
cs.CV2024
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…
cs.CV2023
HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling
Fenggen Yu, Yiming Qian, Francisca Gil-Ureta +3
We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant str…