3 citations · 5 across the 9 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.CV2025
LumiX: Structured and Coherent Text-to-Intrinsic Generation
Xu Han, Biao Zhang, Xiangjun Tang +2
We present LumiX, a structured diffusion framework for coherent text-to-intrinsic generation. Conditioned on text prompts, LumiX jointly generates a comprehensive set of intrinsic…
cs.CV2025
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
Jinfeng Xu, Xianzhi Li, Yuan Tang +5
Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-worl…
cs.CV2025
MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning
Xu Han, Yuan Tang, Jinfeng Xu +1
We introduce Monarch Sparse Tuning (MoST), the first reparameterization-based parameter-efficient fine-tuning (PEFT) method tailored for 3D representation learning. Unlike existing…