Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917231027290112 |
|---|---|
| author | Li, Jianglong Xu, Jun Lu, Bingcong Cheng, Zhengxue Hu, Hongwei Wu, Ronghua Song, Li |
| author_facet | Li, Jianglong Xu, Jun Lu, Bingcong Cheng, Zhengxue Hu, Hongwei Wu, Ronghua Song, Li |
| contents | The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates remains a challenge. Traditional 2D video compression techniques fail to preserve fine-grained geometric and appearance details, while implicit neural rendering methods like NeRF suffer from prohibitive computational costs. To address these challenges, we propose a lightweight, high-fidelity, low-bitrate 3D talking face compression framework that integrates FLAME-based parametric modeling with 3DGS neural rendering. Our approach transmits only essential facial metadata in real time, enabling efficient reconstruction with a Gaussian-based head model. Additionally, we introduce a compact representation and compression scheme, including Gaussian attribute compression and MLP optimization, to enhance transmission efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance, delivering high-quality facial rendering at extremely low bitrates, making it well-suited for real-time 3D video conferencing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21269 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference Li, Jianglong Xu, Jun Lu, Bingcong Cheng, Zhengxue Hu, Hongwei Wu, Ronghua Song, Li Computer Vision and Pattern Recognition Artificial Intelligence The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates remains a challenge. Traditional 2D video compression techniques fail to preserve fine-grained geometric and appearance details, while implicit neural rendering methods like NeRF suffer from prohibitive computational costs. To address these challenges, we propose a lightweight, high-fidelity, low-bitrate 3D talking face compression framework that integrates FLAME-based parametric modeling with 3DGS neural rendering. Our approach transmits only essential facial metadata in real time, enabling efficient reconstruction with a Gaussian-based head model. Additionally, we introduce a compact representation and compression scheme, including Gaussian attribute compression and MLP optimization, to enhance transmission efficiency. Experimental results demonstrate that our method achieves superior rate-distortion performance, delivering high-quality facial rendering at extremely low bitrates, making it well-suited for real-time 3D video conferencing applications. |
| title | Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.21269 |