Research map / 3D vision / 3D generation
Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a pose-aware diffusion prior for extremely sparse-view CT reconstruction from 2D projections, without requiring pre-reconstructed 3D training volumes.
Problem
Extremely sparse-view CT (only a few projections) where dense scans for building 3D training volumes are unavailable, and optimization-based and learned sparse-view methods are limited in this regime.
Approach
Uses diffusion priors conditioned on projection poses so that the prior can be learned and applied directly from 2D projections rather than from pre-reconstructed 3D volumes; details beyond the abstract are not stated.
Closest papers by meaning
- DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction (NeurIPS 2024 · similarity 0.89)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.88)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.87)
- How to Use Diffusion Priors under Sparse Views? (NeurIPS 2024 · similarity 0.87)
- QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction (CVPR 2024 · similarity 0.87)
- Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction (AAAI 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.