activity
20242026
collaborators

6 papers

cs.CV2026

Unwarping the Lens: A Physics-Grounded Approach to Video Glasses Removal

Radim Spetlik, David Futschik, Radek Danecek +4

High-fidelity removal of eyeglasses from video is a major challenge in facial attribute editing, as the underlying facial geometry is often obscured by complex refractive distortio…

cs.CV2026

Talking Together: Synthesizing Co-Located 3D Conversations from Audio

Mengyi Shan, Shouchieh Chang, Ziqian Bai +6

We tackle the challenging task of generating complete 3D facial animations for two interacting, co-located participants from a mixed audio stream. While existing methods often prod…

cs.CV2025

IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos

Yuan Li, Ziqian Bai, Feitong Tan +3

We propose a novel 3D-aware diffusion-based method for generating photorealistic talking head videos directly from a single identity image and explicit control signals (e.g., expre…

cs.CV2024

EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatars

Jianchun Chen, Jian Wang, Yinda Zhang +4

Immersive VR telepresence ideally means being able to interact and communicate with digital avatars that are indistinguishable from and precisely reflect the behaviour of their rea…

cs.CV2024

EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis

Alexander Mai, Peter Hedman, George Kopanas +6

We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recent rasterization based approach by 3D Gauss…

cs.CV2024

LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field

Huan Wang, Feitong Tan, Ziqian Bai +9

Recent works have shown that neural radiance fields (NeRFs) on top of parametric models have reached SOTA quality to build photorealistic head avatars from a monocular video. Howev…