Research map / 3D vision / Face and shape
Expressive Whole-Body 3D Gaussian Avatar
Gyeongsik Moon, Takaaki Shiratori, Shunsuke Saito
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 connectivity-based Laplacian regularizer on Gaussians (ablation) | ExAvatar · NeuMan test (without background) | PSNR: 28.21 -> 34.80 | Improved |
| add connectivity-based Laplacian regularizer on Gaussians (ablation) | ExAvatar · NeuMan test (without background) | LPIPS: 0.199 -> 0.009 | Improved |
| add mesh-based face loss (ablation) | ExAvatar · X-Humans cropped faces | PSNR: 20.02 -> 22.07 | Improved |
| add mesh-based face loss (ablation) | ExAvatar · X-Humans cropped faces | LPIPS: 0.06 -> 0.06 | No clear effect |
| replace Laplacian regularizer with L2 distance to SMPL-X surface (ablation) | ExAvatar · novel poses and expressions | artifacts | Hurt |
| remove pose-conditioned MLPs (ablation) | ExAvatar · Rendering speed | FPS: 26 -> 47 | Improved |
| use monocular RGB video only, without depth, versus X-Avatar with depth | ExAvatar · X-Humans 00028 | PSNR: 28.57 -> 30.58 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 7 of 7 on most shared results.
- X-Avatar — X-Avatar: Expressive Human Avatars (CVPR 2023) · better on 3 of 3 shared results
- Vid2Avatar — Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023) · better on 2 of 2 shared results
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 1 of 1 shared result
- GaussianAvatar — GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (CVPR 2024) · better on 1 of 1 shared result
- HUGS — HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting (CVPR 2024) · better on 1 of 1 shared result
- InstantAvatar — InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds (CVPR 2023) · better on 1 of 1 shared result
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (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
- Expressive Gaussian Human Avatars from Monocular RGB Video (NeurIPS 2024 · similarity 0.92)
- X-Avatar: Expressive Human Avatars (CVPR 2023 · similarity 0.90)
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.87)
- FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024 · similarity 0.87)
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 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.
