Research map / Video / Video generation
Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use the audio-to-landmarks-to-video cascade with DMA, MMCRNN, DAL, and RD | ATVGnet · LRW | PSNR: 29.91 -> 30.91 | Helped |
| use the audio-to-landmarks-to-video cascade with DMA, MMCRNN, DAL, and RD | ATVGnet · GRID | LMD: 1.44 -> 1.29 | Helped |
| add Dynamic Motion & Attention (DMA) (ablation) | ATVGnet · LRW | PSNR: 30.22 -> 33.45 | Helped |
| add Dynamic Motion & Attention (DMA) (ablation) | ATVGnet · GRID | PSNR: 29.90 -> 33.84 | Helped |
| add MMCRNN temporal modeling (ablation) | ATVGnet · LRW | PSNR: 30.61 -> 33.45 | Helped |
| add MMCRNN temporal modeling (ablation) | ATVGnet · GRID | PSNR: 32.68 -> 33.84 | Helped |
| add Dynamically Adjustable Loss (DAL) (ablation) | ATVGnet · LRW | PSNR: 31.35 -> 33.45 | Helped |
| add Dynamically Adjustable Loss (DAL) (ablation) | ATVGnet · GRID | PSNR: 33.11 -> 33.84 | Helped |
| add Regression-based Discriminator (RD) (ablation) | ATVGnet · LRW | PSNR: 32.84 -> 33.45 | Helped |
| add Regression-based Discriminator (RD) (ablation) | ATVGnet · GRID | PSNR: 33.25 -> 33.84 | Helped |
| condition on the last generated frame rather than the example frame (ablation) | ATVGnet · LRW | PSNR: 33.45 -> 30.45 | Hurt |
| condition on the last generated frame rather than the example frame (ablation) | ATVGnet · GRID | PSNR: 33.84 -> 31.78 | Hurt |
Closest papers by meaning
- From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech (CVPR 2025 · similarity 0.88)
- MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation (AAAI 2025 · similarity 0.88)
- DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation (ICLR 2025 · similarity 0.87)
- OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking (NeurIPS 2025 · similarity 0.87)
- Occlusion-Insensitive Talking Head Video Generation via Facelet Compensation (AAAI 2025 · similarity 0.87)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.87)
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.