Picture for Dawei Yang

Dawei Yang

Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

May 10, 2023
Yuyan Ruan, Dawei Yang, Ziqi Tang, An Ran Ran, Carol Y. Cheung, Hao Chen

Figure 1 for Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

Figure 2 for Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

Figure 3 for Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

Figure 4 for Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

* 12 pages, 11 figures

Access Paper or Ask Questions

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Dec 03, 2020
Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng

Figure 1 for Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Figure 2 for Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Figure 3 for Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Figure 4 for Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

* Accepted to NeurIPS 2020

Access Paper or Ask Questions

Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Jun 29, 2019
Dawei Yang, Jia Deng

Figure 1 for Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Figure 2 for Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Figure 3 for Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Figure 4 for Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

Access Paper or Ask Questions

Decorrelated Batch Normalization

Apr 23, 2018
Lei Huang, Dawei Yang, Bo Lang, Jia Deng

Figure 1 for Decorrelated Batch Normalization

Figure 2 for Decorrelated Batch Normalization

Figure 3 for Decorrelated Batch Normalization

Figure 4 for Decorrelated Batch Normalization

* Accepted to CVPR 2018. Code available at https://github.com/umich-vl/DecorrelatedBN

Access Paper or Ask Questions