Research map / 3D vision / Gaussian splatting
Learning Efficient and Generalizable Human Representation with Human Gaussian Model
Yifan Liu, Shengjun Zhang, Chensheng Dai, Yang Chen, Hao Liu, Chen Li, Yueqi Duan
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 intra-node operation (cross-frame aggregation on mesh vertices) (ablation) | Human Gaussian Graph · MvHumanNet novel pose, multi-view | PSNR: 21.902 -> 24.013 | Improved |
| add inter-node operation (message passing between neighboring mesh vertices) (ablation) | Human Gaussian Graph · MvHumanNet novel pose, multi-view | PSNR: 23.105 -> 24.013 | Improved |
| add learnable mesh-aligned queries without graph operations (ablation) | Baseline binding Gaussians to SMPL · MvHumanNet novel pose, multi-view | PSNR: +0.57 PSNR | Improved |
| increase number of stacked intra/inter layers from 1 to 6 (ablation) | Human Gaussian Graph · MvHumanNet novel pose, multi-view | PSNR: 23.455 -> 24.013 | Improved |
| gather information across frames instead of using a single frame | LGM · MvHumanNet single-view novel view | PSNR: 21.274 -> 23.112 | Improved |
| swap in stronger single-frame backbone IDOL under HGG | Human Gaussian Graph · Deepfashion | PSNR: 20.31 -> 22.38 | Improved |
| use single-view input with diffusion-generated views instead of multi-view input | Human Gaussian Graph · MvHumanNet | PSNR: 3.4 dB lower | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- GART — GART: Gaussian Articulated Template Models (CVPR 2024) · better on 2 of 2 shared results
- GPS-Gaussian — GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis (CVPR 2024) · better on 1 of 2 shared results
- IDOL — IDOL: Inertial Deep Orientation-Estimation and Localization (AAAI 2021) · better on 2 of 2 shared results
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
- Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs (CVPR 2025 · similarity 0.91)
- Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (CVPR 2024 · similarity 0.90)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.90)
- Generalizable Human Gaussians from Single-View Image (ICLR 2025 · similarity 0.90)
- GauHuman: Articulated Gaussian Splatting from Monocular Human Videos (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
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.
