Research map / 3D vision / Face and shape
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation
Shan He, Haonan He, Shuo Yang, Xiaoyan Wu, Pengcheng Xia, Bing Yin, Cong Liu, Lirong Dai, Chang Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| pretrain FaceFormer on speech-assisted reconstructed 4D data | FaceFormer · VOCASET test | lip vertex error: 5.355e-3 -> 4.863e-3 | Improved |
| add speech-visual contrastive loss to reconstruction (ablation) | Speech4Mesh pretraining data · VOCASET test | lip vertex error: 5.271e-3 -> 4.863e-3 | Improved |
| add photometric loss during audio2mesh pretraining (ablation) | Speech4Mesh · VOCASET test | lip vertex error: 5.233e-3 -> 4.863e-3 | Improved |
| remove contrastive loss, pretrained model vs vanilla FaceFormer (ablation) | Speech4Mesh · VOCASET test | lip vertex error: 5.355e-3 -> 5.271e-3 | Improved |
| use speech-assisted reconstruction instead of EMOCA | monocular 3D face reconstruction · VOCASET | lip vertex error: 1.359e-2 -> 0.995e-2 | Improved |
| add emotion code to pretraining | FaceFormer · emotion control | qualitative | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EMOCA — EMOCA: Emotion Driven Monocular Face Capture and Animation (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition (AAAI 2025 · similarity 0.89)
- Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications (CVPR 2024 · similarity 0.88)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (AAAI 2024 · similarity 0.88)
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio (CVPR 2024 · similarity 0.88)
- DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI 2025 · similarity 0.88)
- Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics (CVPR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
