Research map / 3D vision / Face and shape
InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds
Tianjian Jiang, Xu Chen, Jie Song, Otmar Hilliges
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 dynamic empty-space skipping during training and rendering (ablation) | InstantAvatar · PeopleSnapshot | training time per 100 epochs: 3m 10s -> 1m 47s | Improved |
| Add dynamic empty-space skipping during rendering (ablation) | InstantAvatar · PeopleSnapshot | rendering speed: ~ 1 FPS -> ~ 15 FPS | Improved |
| Add occupancy-based regularization (ablation) | InstantAvatar · PeopleSnapshot, 4 sequences | PSNR: 28.22 -> 28.64 | Improved |
| Add occupancy-based regularization (ablation) | InstantAvatar · PeopleSnapshot, 4 sequences | LPIPS: 0.0301 -> 0.0240 | Improved |
| Use global sparsity instead of occupancy-based regularization (ablation) | InstantAvatar · PeopleSnapshot | image quality | Hurt |
| Use InstantAvatar rather than Anim-NeRF for novel-pose synthesis | Avatar reconstruction · SURREAL S1-S3 | PSNR: 21.66 -> 24.48; 20.00 -> 23.94; 20.06 -> 25.08 | Improved |
| Use InstantAvatar rather than Anim-NeRF on PeopleSnapshot | Avatar reconstruction · PeopleSnapshot, four subjects | PSNR: 29.37 -> 29.65; 28.37 -> 27.97; 28.91 -> 27.90; 28.90 -> 28.92 | Mixed |
Later papers that compared with this method
12 later accepted papers report InstantAvatar as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos (AAAI 2026 · better on 3 of 3 shared results)
- JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video (ECCV 2026 · better on 1 of 1 shared result)
- TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model (CVPR 2025 · better on 0 of 3 shared results)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · better on 0 of 1 shared result)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · better on 8 of 8 shared results)
- GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (CVPR 2024 · better on 6 of 6 shared results)
- Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses (CVPR 2024 · better on 3 of 3 shared results)
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · better on 3 of 3 shared results)
4 more not listed.
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
- Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023 · similarity 0.90)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.90)
- Instant Volumetric Head Avatars (CVPR 2023 · similarity 0.89)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (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.
