Research map / 3D vision / Human pose estimation
SparsePose: Sparse-View Camera Pose Regression and Refinement
Samarth Sinha, Jason Y. Zhang, Andrea Tagliasacchi, Igor Gilitschenski, David B. Lindell
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 |
|---|---|---|---|
| Use learned pose regression and iterative 3D-consistent refinement instead of conventional feature-matching pose estimation | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Use learned pose regression and iterative 3D-consistent refinement instead of conventional feature-matching pose estimation | SparsePose · CO3D test categories, sparse views | cameras within 20% of scene scale | Improved |
| Initialize cameras with SparsePose before novel-view synthesis | Sparse-view NeRFormer with BARF refinement · CO3D test categories, sparse-view novel-view synthesis | PSNR | Improved |
| Initialize cameras with SparsePose before novel-view synthesis | Sparse-view NeRFormer with BARF refinement · CO3D test categories, sparse-view novel-view synthesis | LPIPS | Improved |
| Add iterative pose refinement after initial pose regression (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Resample 3D points between refinement iterations (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Use autoregressive refinement (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Add positional encoding to refinement inputs (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Use pretrained image features rather than RGB values for refinement (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
| Use a robust loss function (ablation) | SparsePose · CO3D test categories, sparse views | cameras within 15° rotation error | Improved |
Closest papers by meaning
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.94)
- LEAP: Liberate Sparse-View 3D Modeling from Camera Poses (ICLR 2024 · similarity 0.92)
- Cameras as Rays: Pose Estimation via Ray Diffusion (ICLR 2024 · similarity 0.90)
- No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images (ICLR 2025 · similarity 0.89)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.89)
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images (CVPR 2025 · similarity 0.88)
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.
