Research map / 3D vision / NeRF and radiance fields
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling
YoungJoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs
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 |
|---|---|---|---|
| Combine the implicit body NeRF with image-based rendering and learned appearance blending | NIA · ZJU-MoCap, unseen subjects and poses | PSNR: +1.0 dB PSNR | Improved |
| Use NIA instead of NHP for cross-dataset generalization | ZJU-MoCap-trained model evaluated on MonoCap · MonoCap, cross-dataset novel view synthesis | PSNR: +1.6 dB PSNR | Improved |
| Add the implicit body representation (ablation) | NIA · ZJU-MoCap, unseen identities and poses | PSNR: -1.63 dB | Improved |
| Add image-based rendering (ablation) | NIA · ZJU-MoCap, unseen identities and poses | PSNR: -1.55 dB | Improved |
| Use learned neural appearance blending instead of simple averaging (ablation) | NIA · ZJU-MoCap, unseen identities and poses | PSNR: +0.97 dB | Improved |
| Use learned neural appearance blending instead of cosine-similarity weighted averaging (ablation) | NIA · ZJU-MoCap, unseen identities and poses | PSNR: +0.45 dB | Improved |
| Increase the number of source views from 1 to 2 to 3 (ablation) | NIA · ZJU-MoCap, novel view synthesis | PSNR | Improved |
Closest papers by meaning
- Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering (NeurIPS 2021 · similarity 0.90)
- MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning (AAAI 2025 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Pose Modulated Avatars from Video (ICLR 2024 · similarity 0.88)
- NECA: Neural Customizable Human Avatar (CVPR 2024 · similarity 0.88)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · 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.
