This weekend I attended 22nd annual ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2023) in sunny Los Angeles, California. The conference was held at the UCLA campus. This was my second SCA conference - last year I attended the 2022 edition in Durham. However, this year I was attending to present my paper NeuroDog: Quadruped Embodiment using Neural Networks. I presented the paper in the Character Synthesis session on day two of the conference. The paper has also been accepted for journal publication in Proceedings of the ACM in Computer Graphics and Interactive Techniques (PACMCGIT) special issue on SCA.

Santa Monica

In the paper, we present our novel virtual reality (VR) quadruped embodiment system called NeuroDog. NeuroDog is the first VR quadruped embodiment system to use deep learning to synthesise realistic motion for the virtual quadruped. The user, viewing themselves as a quadruped from a first-person perspective, is able to perform different actions in a natural, intuitive and relatively unconstrained manner. The virtual quadruped mimics their actions, switching gaits as the user moves faster or slower, sitting as the user sits, or raising its paws as the user raises their legs. The core novelty within NeuroDog is a novel architecture, built using two neural networks, for the real-time mapping of natural human motion to realistic quadruped motion. The architecture is designed to preserve the synchrony between the user’s legs and the virtual quadruped’s front legs when performing tasks such as locomotion or paw-raises. We also present new perceptual results regarding virtual animal embodiment. Check out the paper for all the details!

It was great to see all the other amazing paper presentations together with some really interesting key-notes!