arXiv subjects

Victor Oei

Publications and source records attributed to Victor Oei.

3 recordsLinked to original sources

arXiv2026

Multi-objective computational design optimization of a Total Disc Replacement implant

While cervical arthroplasty using Total Disc Replacement (TDR) implants is an established treatment for persistent neck and arm pain, revision rates limit it from reaching its full potential. To address the underlying complications, we developed finite element simulation-driven design optimizations for a TDR's bone-implant interface and motion-preservation features. These automated processes explored high-dimensional design spaces iteratively through analysis of design variations interplay with spinal structures. The optimizations were metamodel-based using artificial neural networks and a hybrid optimizer. They optimized the motion-preservation zone towards replicating the asymptomatic spinal segment's ligaments strain profiles and its facet joint force profiles during main motions. This design process aims to minimize the risk for postoperative pain, avoidable degeneration and to restore segmental biomechanics, to prevent adjacent segment effects. Designs with single articulation and with dual articulation (with a mobile insert) were optimized. The bone-implant interface was optimized with the aim to minimize the risk for subsidence and implant migration. The optimizations improved the multi-objective value of the bone-implant interface by 14.6% and that of the motion-preservation zone by 36.1%. Implant migration, the leading cause of revisions, was reduced by 24.8%. With this, we show the potential of simulation-driven implant design optimization for addressing complex clinical challenges.

cs.CE↗

arXiv2025

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork

We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly and selects them adaptively based on a learnability criterion, removing the need for pre-trained partner populations or manual parameter tuning. We show that this simple mechanism enables effective partner diversity and can be extended to joint partner-environment selection when a procedural level generator is available. Across Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, UPD consistently achieves strong performance compared to both population-based and population-free baselines. In a human-AI user study, agents trained with UPD achieve higher returns and are rated as more adaptive, more human-like, and less frustrating than all evaluated baseline methods.

cs.LG↗

arXiv2025

RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world perturbations is largely unquantified. To address this, we present RobustSpring, a comprehensive dataset and benchmark for evaluating robustness to image corruptions for optical flow, scene flow, and stereo models. RobustSpring applies 20 different image corruptions, including noise, blur, color changes, quality degradations, and weather distortions, in a time-, stereo-, and depth-consistent manner to the high-resolution Spring dataset, creating a suite of 20,000 corrupted images that reflect challenging conditions. RobustSpring enables comparisons of model robustness via a new corruption robustness metric. Integration with the Spring benchmark enables two-axis evaluations of both accuracy and robustness. We benchmark a curated selection of initial models, observing that robustness varies widely by corruption type, and experimentally show that evaluations on RobustSpring indicate real-world robustness. RobustSpring is a new computer vision benchmark to treat robustness as a first-class citizen, fostering models that are accurate and resilient. It is available at https://spring-benchmark.org.

cs.CV↗