Research map / 3D vision / Face and shape
UniRestore3D: A Scalable Framework For General Shape Restoration
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 UniRestore3D, a scalable framework for general 3D shape restoration that handles multiple simultaneous defect types (incomplete, noisy, low-resolution) rather than single-subtask generative models.
Problem
Recovering intact 3D shapes from defective ones when multiple defect types occur simultaneously; prior generative methods handle only specific defect subtasks and are limited by small training data.
Approach
A unified, scalable framework for general shape restoration that targets combined defects (incomplete, noisy, low-resolution) instead of training separate specialized generative models per subtask.
Closest papers by meaning
- A Field Model for Repairing 3D Shapes (CVPR 2016 · similarity 0.87)
- Unsupervised 3D Shape Completion Through GAN Inversion (CVPR 2021 · similarity 0.87)
- Learning to Reconstruct Shapes from Unseen Classes (NeurIPS 2018 · similarity 0.87)
- Deep Optimized Priors for 3D Shape Modeling and Reconstruction (CVPR 2021 · similarity 0.86)
- Make-A-Shape: a Ten-Million-scale 3D Shape Model (ICML 2024 · similarity 0.86)
- ZeroShape: Regression-based Zero-shot Shape Reconstruction (CVPR 2024 · similarity 0.85)
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.