Research map / 3D vision / Face and shape
InteractAvatar: Modeling Hand-Face Interaction in Photorealistic Avatars with Deformable Gaussians
Kefan Chen, Sreyas Mohan, Justin Theiss, Sergiu Oprea, Srinath Sridhar, Aayush Prakash
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 PointNet++ geometric feature (ablation) | InteractAvatar · DECAF novel view (subject 4) | PSNR: 28.93 -> 29.85 | Improved |
| add PointNet++ geometric feature (ablation) | InteractAvatar · DECAF novel view (subject 4) | LPIPS: 0.0370 -> 0.0338 | Improved |
| add dynamic hand MLPs H (ablation) | InteractAvatar · DECAF novel view (subject 4) | PSNR: 26.97 -> 29.85 | Improved |
| add dynamic hand MLPs H (ablation) | InteractAvatar · DECAF novel view (subject 4) | LPIPS: 0.0574 -> 0.0338 | Improved |
| add dynamic hand MLPs H (ablation) | InteractAvatar · DECAF novel view (subject 4) | SSIM: 0.9359 -> 0.9335 | Hurt |
| add hand-face interaction MLPs I (ablation) | InteractAvatar · DECAF novel view (subject 4) | PSNR: 28.23 -> 29.85 | Improved |
| add hand-face interaction MLPs I (ablation) | InteractAvatar · DECAF novel view (subject 4) | LPIPS: 0.0467 -> 0.0338 | Improved |
| add hand-face interaction MLPs I (ablation) | InteractAvatar · DECAF novel view (subject 4) | SSIM: 0.9389 -> 0.9335 | Hurt |
| use InteractAvatar instead of GaussianAvatar | GaussianAvatar · DECAF novel view | PSNR: 26.71 -> 29.85 | Improved |
| use InteractAvatar instead of GaussianAvatar | GaussianAvatar · DECAF self-enactment | SSIM: 0.9393 -> 0.9356 | Hurt |
| use InteractAvatar instead of GaussianAvatar | GaussianAvatar · DECAF self-enactment | LPIPS: 0.0578 -> 0.0396 | Improved |
| add patch perceptual loss Lpatch (ablation) | InteractAvatar · DECAF (qualitative) | visual detail | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GaussianAvatar — GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (CVPR 2024) · better on 5 of 6 shared results
- SplattingAvatar — SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024) · better on 6 of 6 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
- Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars (NeurIPS 2024 · similarity 0.90)
- OHTA: One-shot Hand Avatar via Data-driven Implicit Priors (CVPR 2024 · similarity 0.87)
- HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation (AAAI 2025 · similarity 0.87)
- MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation (NeurIPS 2025 · similarity 0.87)
- AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation (ICLR 2025 · similarity 0.87)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · 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.
