Research map / 3D vision / Gaussian splatting
Animatable Gaussian human avatars
Represents animatable humans and heads with pose-dependent or mesh-embedded Gaussians.
14 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2024–2026) · an approach in Gaussian splatting, keyword cluster “dynamic · 4d · motion”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
5 papers in 2023–24 and 9 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 4.1% to 1.3%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2024 · Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (CVPR 2024 · 147 citations)
- 2025 · AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction (CVPR 2025 · 13 citations)
- 2026 · Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting (CVPR 2026 · 1 citation)
Earliest papers here
- Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (CVPR 2024 · 147 citations)
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · 136 citations)
- HUGS: Human Gaussian Splats (CVPR 2024 · 135 citations)
What has been tried
11 papers here report 122 measured changes (a component added, removed or swapped, compared with a baseline): helped 67%, no clear effect 8%, hurt 23%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Replace the character-specific template with SMPL-X | Novel pose synthesis · visual avatar quality | Hurt | Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (CVPR 2024 · 147 citations) | |
| Remove trainable mesh embedding and use fixed embedding with a trainable local shift | Novel-pose rendering · rendering quality | Hurt | SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · 136 citations) | |
| Add learned LBS weights for Gaussian animation | NeuMan human-only bounding boxes, Seattle · PSNR | 18.47 -> 19.06 | Helped | HUGS: Human Gaussian Splats (CVPR 2024 · 135 citations) |
| add motion conditioning | DynaCap novel pose, Loose Outfits · LPIPS | 32.35 -> 20.22 | Helped | ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering (CVPR 2024 · 71 citations) |
| remove the mesh and use 3D Gaussians only | ZJU-MoCap novel view synthesis · PSNR | 30.36 -> 30.06 | Hurt | GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh (CVPR 2024 · 45 citations) |
| replace 3DGS with 4DGS reconstruction | Human4DiT synthetic datasets, reconstruction · FID | 114.645 -> 77.879 | Helped | AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction (CVPR 2025 · 13 citations) |
| add feature-line blendshapes | Novel View Synthesis, subject #306 · PSNR | 33.4206 -> 33.4337 | Helped | 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · 4 citations) |
| add learned clothing deformations to the reposed model | 4D-Dress · PSNR | 23.94 -> 25.46 | Helped | Disco4D: Disentangled 4D Human Generation and Animation from a Single Image (CVPR 2025 · 4 citations) |
| replace the linear transformation on µ with a 3-layer MLP | INSTA dataset · PSNR | 31.93 -> 31.74 | Hurt | GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · 4 citations) |
| Use the anisotropic constitutive model | ActorsHQ test · CD (×10^3) | 6.24 -> 0.42 | Helped | MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · 1 citation) |
| Add the hair-to-body SDF constraint | Hair deformation test sets · Error (L2) | 0.1269 -> 0.0832 | Helped | DGH: Dynamic Gaussian Hair (NeurIPS 2025 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 7 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- 4D-Dress · 2 of 7 papers
Baselines
- CHAMP · 2 of 7 papers
- LGM · 2 of 7 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 14 papers; from OpenAlex and the papers' affiliations).
- ETH Zurich · 2 papers
- Meta · 2 papers
Use it
Download BibTeX of 14 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Deformable 4D Gaussian splatting (112 papers)
- Monocular dynamic scene reconstruction (80 papers)
Elsewhere in the topic
- Compact and efficient Gaussian splatting (269 papers)
- Regularization and primitive design for 3DGS (213 papers)
- Sparse-view Gaussian splatting for novel views (111 papers)
- Animatable Gaussian human avatars (42 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).