Research map / 3D vision / Face and shape
Robust 3D Self-Portraits in Seconds
Zhe Li, Tao Yu, Chuanyu Pan, Zerong Zheng, Yebin Liu
Check 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 the learned inner-layer shape prior to non-rigid fusion (ablation) | PIFusion · 3D self-portrait reconstruction | tracking and reconstruction accuracy | Improved |
| Add outer-layer depth correspondences (ablation) | PIFusion · 3D self-portrait reconstruction | reconstruction accuracy | Improved |
| Add non-rigid volumetric deformation to refine the inner model (ablation) | PIFusion · 3D self-portrait reconstruction | reconstruction accuracy | Improved |
| Add the live silhouette term (ablation) | Lightweight Bundle Adjustment · 3D self-portrait reconstruction | silhouette consistency | Improved |
| Add bundle adjustment after PIFusion (ablation) | PIFusion · 3D self-portrait reconstruction | loop-closure and portrait accuracy | Improved |
| Jointly optimize bundle deformations and live warp fields (ablation) | Lightweight Bundle Adjustment · Bundle adjustment optimization | total energy | Improved |
| Use Bundle Adjustment instead of PIFusion alone (ablation) | PIFusion · Case lz, chest circumference (cm) | chest circumference (cm): 97.6 -> 94.6 | Improved |
| Use Bundle Adjustment instead of PIFusion alone (ablation) | PIFusion · Case lz, waist circumference (cm) | waist circumference (cm): 87.2 -> 84.5 | Improved |
| Use Bundle Adjustment instead of PIFusion alone (ablation) | PIFusion · Case lz, right knee circumference (cm) | right knee circumference (cm): 40.7 -> 39.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DoubleFusion — DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth Sensor (CVPR 2018) · better on 3 of 3 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
- Robust and Accurate 3D Self-Portraits in Seconds (TPAMI 2021 · similarity 0.97)
- POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture (CVPR 2021 · similarity 0.86)
- UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections (ICLR 2026 · similarity 0.85)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.83)
- Coherent 3D Portrait Video Reconstruction via Triplane Fusion (CVPR 2025 · similarity 0.82)
- SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting (CVPR 2025 · similarity 0.82)
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.
