Research map / 3D vision / Depth and stereo
X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
Feiran Wang, Jiachen Tao, Junyi Wu, Haoxuan Wang, Bin Duan, Kai Wang, Zongxin Yang, Yan Yan
Read the paperCheck your idea against 137,217 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 X-Field, a physically informed 3D representation for X-ray reconstruction that targets both X-ray novel view synthesis and CT reconstruction with reduced radiation dose.
Problem
Existing 3D reconstruction representations, borrowed for X-ray novel view synthesis and CT reconstruction, fail to fully capture the penetration and attenuation properties of X-rays, limiting reduced-dose imaging.
Approach
A representation explicitly built on X-ray physics (penetration and attenuation) rather than generic 3D reconstruction primitives, applied to both X-ray NVS and CT reconstruction.
Closest papers by meaning
- Structure-Aware Sparse-View X-ray 3D Reconstruction (CVPR 2024 · similarity 0.89)
- X-Ray: A Sequential 3D Representation For Generation (NeurIPS 2024 · similarity 0.89)
- Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis (ECCV 2024 · similarity 0.87)
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction (NeurIPS 2024 · similarity 0.85)
- DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering (NeurIPS 2024 · similarity 0.85)
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.84)
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.
