Muhammad Asim — accepted AI-conference papers

2024

DistillGrasp: Integrating Features Correlation With Knowledge Distillation for Depth Completion of Transparent Objects

Yiheng Huang, Junhong Chen, Nick Michiels, Muhammad Asim, Luc Claesen, Wenyin Liu

RA-L 2024

Due to the visual properties of reflection and refraction, RGB-D cameras cannot accurately capture the depth of transparent objects, leading to incomplete depth maps. To fill in the missing points, recent studies tend to explore new visual features and design complex networks to reconstruct the dept

Cited by 5 Source ↗Scholar ↗

2020

Invertible generative models for inverse problems: mitigating representation error and dataset bias

Muhammad Asim, Max Daniels, Oscar Leong, Ali Ahmed, Paul Hand

ICML 2020poster

Trained generative models have shown remarkable performance as priors for inverse problems in imaging – for example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any par…

Cited by 173 Source ↗PDF ↗code ↗Scholar ↗