Research map / 3D vision / Face and shape
Neural Refraction Fields for Image Verification
Sage Simhon, Jingwei Ma, Prafull Sharma, Lucy Chai, Yen-Chen Lin, Phillip Isola
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 an image verification approach that embeds a private authenticity signature via physical refractive objects that transform the image, and detects tampering by comparing the image to a pixel-aligned reconstruction from the embedding.
Problem
Verifying whether visual media has been tampered with, as image manipulation capabilities improve.
Approach
Embeds a private authenticity signature into an image using physical refractive objects that transform the image; verification compares the image with a pixel-aligned reconstruction derived from the embedding to find inconsistencies.
Closest papers by meaning
- Neural Transmitted Radiance Fields (NeurIPS 2022 · similarity 0.86)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.85)
- Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022 · similarity 0.85)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.84)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.84)
- From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS (NeurIPS 2024 · similarity 0.83)
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.
