Research map / 3D vision / Human pose estimation
An Interactive Conversational 3D Virtual Human
Richard Shaw, Youngkyoon Jang, Athanasios Papaioannou, Arthur Moreau, Helisa Dhamo, Zhensong Zhang, Eduardo Pérez-Pellitero
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 spatial-temporal feature encoder (SWinGS to SWinGS++) | SWinGS · DNA-Rendering body NVS | PSNR: 29.4488 -> 30.1701 | Improved |
| use sliding-window 4D Gaussians instead of Spacetime Gaussians | dynamic body model · DNA-Rendering body NVS | PSNR: 29.3039 -> 29.4488 | Improved |
| use time-dependent 4D model SWinGS++ instead of animatable skinned HuGS | avatar body · DNA-Rendering body NVS | PSNR: 25.0400 -> 30.1701 | Improved |
| use HeadGaS++ instead of TalkingGaussian | talking head · self-reconstruction | PSNR: 29.317 -> 30.398 | Improved |
| use HeadGaS++ instead of TalkingGaussian | talking head · self-reconstruction | FPS: 110 -> 250 | Improved |
| use HeadGaS++ instead of TalkingGaussian | talking head · self-reconstruction | LPIPS: 0.046 vs 0.051 | No clear effect |
| render head on top of body and background on RTX 4090 laptop vs body only (ablation) | interactive viewer · Windows viewer | FPS: 169.92 -> 105.27 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- HuGS — HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting (CVPR 2024) · better on 4 of 4 shared results
- TalkingGaussian — TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting (ECCV 2024) · better on 4 of 4 shared results
- RAD-NeRF — Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024) · 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
- TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image (NeurIPS 2025 · similarity 0.88)
- Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 2024 · similarity 0.88)
- From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations (CVPR 2024 · similarity 0.87)
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024 · similarity 0.86)
- VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time (NeurIPS 2024 · similarity 0.86)
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.
