Signals 4 · free daily AI digest

MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling

Paper recorded by Signals 4 on 2026-09-11 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.CV · 计算机视觉 · first seen 2026-09-14

Abstract

Accurate head modeling requires a stable yet expressive geometric representation. Existing Gaussian-based head avatars commonly rely on parametric templates (e.g., FLAME) for Gaussian initialization and deformation, but these templates lack personalized priors and struggle to represent structures such as hair and clothing. To address this issue, we propose MGAvatar, a Gaussian-mesh hybrid represen

Read on arXiv →

#78 most recent of 237 cs.CV papers we have recorded · ↑ newer: 3D CT-to-PET Translation via Latent Brownian Bridge Diffusion · ↓ older: SenseNova-U1.5: Towards Native Unified Visual Intelligence
Cite this page: MGAvatar: Mesh-Bound Gaussians for Head Avatar Geometry and Appearance Modeling: the #78 most recent of 237 cs.CV papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/mgavatar-mesh-bound-gaussians-for-head-avatar-geometry-and-appearance-modeling.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions