Matthew Chan — accepted AI-conference papers

2025

Coherent 3D Portrait Video Reconstruction via Triplane Fusion

Shengze Wang, Xueting Li, Chao Liu, Matthew Chan, Michael Stengel, Henry Fuchs +2

CVPR 2025poster

Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker +2

CVPR 2024poster

3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet the significant memory and computational costs of dense sampling in volume re…

Cited by 8 Source ↗PDF ↗Scholar ↗