Research map / 3D vision / Face and shape
FAMOUS: High-Fidelity Monocular 3D Human Digitization Using View Synthesis
Vishnu Mani Hema, Shubhra Aich, Christian Haene, Jean-Charles Bazin, Fernando de la Torre
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 |
|---|---|---|---|
| add Coral domain adaptation loss to simultaneous training of the hallucinator (ablation) | Distributionally Aligned Hallucinator · RenderPeople | FID: 71.0900 -> 72.5376 | Hurt |
| add MMD domain adaptation loss to simultaneous training (ablation) | Distributionally Aligned Hallucinator · RenderPeople | FID: 71.0900 -> 73.0580 | Hurt |
| add SIREN sine activation to Tex-PIFu color MLP (ablation) | Tex-PIFu* · RenderPeople texture | FID: 103.4353 -> 78.3775 | Improved |
| add UNet backbone on top of SIREN (ablation) | FAMOUS texture completion · RenderPeople texture | FID: 78.3775 -> 55.0711 | Improved |
| add semantic and pose alignment stages instead of naive fine-tuning of hallucinator (ablation) | hallucinator · RenderPeople back-view synthesis | qualitative | Improved |
| use PIFu-HD occupancy network instead of ICON or ECON (ablation) | FAMOUS shape · RenderPeople fashion images | qualitative | Improved |
Closest papers by meaning
- MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement (AAAI 2025 · similarity 0.82)
- Towards Robust Monocular Depth Estimation: A New Baseline and Benchmark (IJCV 2024 · similarity 0.82)
- Sharp Monocular View Synthesis in Less Than a Second (ICLR 2026 · similarity 0.82)
- 4D-Fly: Fast 4D Reconstruction from a Single Monocular Video (CVPR 2025 · similarity 0.80)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.80)
- LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors (CVPR 2025 · similarity 0.80)
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.
