UNeR3D: Versatile and Scalable 3D RGB Point Cloud Generation from 2D Images in Unsupervised Reconstruction

no code implementations • 10 Dec 2023 • Hongbin Lin, Juangui Xu, Qingfeng Xu, Zhengyu Hu, Handing Xu, Yunzhi Chen, Yongjun Hu, Zhenguo Nie

Our model significantly cuts down the training costs tied to supervised approaches and introduces RGB coloration to 3D point clouds, enriching the visual experience.

3D Reconstruction Point Cloud Generation

How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking

1 code implementation • 4 Dec 2023 • Zhengyu Hu, Jieyu Zhang, Yue Yu, Yuchen Zhuang, Hui Xiong

This paper presents LEMR (Label-Efficient Model Ranking) and introduces the MoraBench Benchmark.

Model Selection

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

no code implementations • NeurIPS 2023 • Jieyu Zhang, Bohan Wang, Zhengyu Hu, Pang Wei Koh, Alexander Ratner

Pre-training datasets are critical for building state-of-the-art machine learning models, motivating rigorous study on their impact on downstream tasks.