On-the-fly Gaussian Splatting for Vehicle Surround View
We are building a surround view for vehicles on top of an explicit 3D scene representation. Four fisheye cameras are mounted on the vehicle body — front, rea...
Our Research Field
Engineering the imaging stack. Graphics × Vision × Generative AI — from in-house rendering engines and inverse graphics to Gaussian Splatting, sim-to-real learning, and domain-tuned perception.
Projects
Real2Sim & Sim2Real — Aligning Dynamics Across Physics Systems
Two physics systems never agree. Record a vehicle following a path — in the real world, or in another simulator — then feed exactly the same steering and thr...
Physics-Ready Assets and Digital Twins
A reconstructed scene is not yet a world. Photometric reconstruction — a Gaussian-splat map, a mesh, a radiance field — tells you what a place looks like, bu...
Sketch-based Hair Editing with Generative Priors
We work on sketch-driven hair editing for portrait images. The user draws coloured strokes over a photograph — indicating where hair should go, how it should...
Modern In-house Real-time Graphics Engine
We develop a modern in-house real-time graphics engine (VizMotive) built on a contemporary architecture, integrating production-quality rendering features ad...
Dental Realistic Inverse Graphics
We turn a single-material 3D mesh equipped with semantic part labels (enamel, gum, dentin, per-tooth IDs) into a full pipeline for photorealistic dental imag...
AR Navigation-based Surgical Guidance System
We have developed an AR navigation-based surgical guidance system that augments a surgeon’s view with intra-operative imaging and tool-tracking information. ...
Auto- Vehicle Asistantance Imaging
We have been interested in technology development that combines computer graphics and computer vision, and recently, we have been conducting the development ...
Immersive Extended Reality Experience
Building on our experience in computer graphics and computer vision, we develop immersive extended reality (XR) experiences that combine the latest Unreal En...
GAN-Inversion with StyleGAN2
We have explored GAN-inversion with StyleGAN2 as a powerful tool for high-fidelity hairstyle manipulation. Building on the latent-space structure of StyleGAN...
Rendering and Visualization
We have been developing our own rendering engine for over 10 years since 2010, and have extensive experience in successfully applying it to commercial visual...
Sensor Imaging
Our Expertise in Industrial Vision Solutions