Wenxin Liu

I recently completed my Master’s degree in Computer Science at Birkbeck, University of London, under the supervision of Prof. Tobias Ritschel (UCL), where my research focused on the intersection of computer graphics and machine learning. In particular, applying neural networks to bounding volumes and spatial queries, shifting construction from a problem in computational geometry to a problem of optimisation. Our article, “Neural Bounding”, is out on arXiv pre-print.

Alongside my academic pursuits, I am a senior engineer with a decade of industry experience. My professional expertise spans across data, infrastructure, platform, and software. In particular, I specialised extensively in Site Reliability Engineering (distributed systems, networking, platforms, pipelines, telemetry, Linux, cloud computing) and Software Engineering (object-oriented: Go, Java, Python; Functional: Scala, Kotlin.)

I received my BSc (Hons) from University College London. Looking ahead, I’m interested in pursuing further research via a Ph.D. that combines computer graphics and computer vision.

You can get in touch with me at wenxin.liu.cs[at]gmail.com.

Latest publication

Neural Bounding

Wenxin Liu, Michael Fischer, Paul D. Yoo, and Tobias Ritschel

arXiv pre-print, 2023

Abs HTML PDF

Bounding volumes are an established concept in computer graphics and vision tasks but have seen little change since their early inception. In this work, we study the use of neural networks as bounding volumes. Our key observation is that bounding, which so far has primarily been considered a problem of computational geometry, can be redefined as a problem of learning to classify space into free and empty. This learning-based approach is particularly advantageous in high-dimensional spaces, such as animated scenes with complex queries, where neural networks are known to excel. However, unlocking neural bounding requires a twist: allowing – but also limiting – false positives, while ensuring that the number of false negatives is strictly zero. We enable such tight and conservative results using a dynamically-weighted asymmetric loss function. Our results show that our neural bounding produces up to an order of magnitude fewer false positives than traditional methods.