Daniel Stanley Tan

About

Daniel Stanley Tan is a researcher at the forefront of computer vision and robotics, with a focus on 3D perception and generative models. His work centers on solving critical challenges in depth inference, object completion, and robotic autonomy—key enablers for smart homes, smart cities, and industrial automation. Tan’s major contributions include pioneering the use of generative adversarial networks (GANs) for single-image depth estimation and 3D object completion, as demonstrated in his 2018 paper on class-conditional GANs for 3D object completion (11 citations) and his 2019 work on single-image depth inference (10 citations). He also advanced depth map upsampling through multi-modal GANs (8 citations), addressing sensor limitations in robotics. More recently, Tan explored collaborative robotic inspection for anomaly detection in industrial settings (3 citations). His research has garnered over 30 citations, reflecting its growing impact on practical perception tasks like robot grasping, obstacle avoidance, and navigation. Tan’s innovative use of GANs to bridge the gap between RGB and depth data positions him as a rising voice in applied AI for autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   3D Object Completion via Class-Conditional Generative Adversarial Network

   11 citations · 2018
2. 2
   Single-Image Depth Inference Using Generative Adversarial Networks

   10 citations · 2019
3. 3
   Depth Map Upsampling via Multi-Modal Generative Adversarial Network

   8 citations · 2019
4. 4
   A Collaborative Robotic Approach for Inspection and Anomaly Detection in Industrial Applications

   3 citations · 2021

Key Collaborators

Contact & Links