Research map / 3D vision / 3D generation
3D Common Corruptions and Data Augmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add 3D data augmentation to O+DPT+2DCC | O+DPT+2DCC · 3DCC | ℓ1 error: 5.94 -> 5.42 | Helped |
| Add 3D data augmentation to O+DPT+2DCC | O+DPT+2DCC · AE | ℓ1 error: 6.50 -> 4.94 | Helped |
| Add 3D data augmentation to O+DPT+2DCC | O+DPT+2DCC · 2DCC | ℓ1 error: 5.78 -> 5.32 | Helped |
| Add 3D data augmentation to O+DPT+2DCC | O+DPT+2DCC · OASIS validation | angular error: 23.67 -> 24.65 | Hurt |
| Add 2DCC data augmentation | O+DPT · 3DCC | ℓ1 error: 6.13 -> 5.94 | Helped |
| Add cross-task consistency constraints | Ours · AE | ℓ1 error: 4.94 -> 5.47 | Hurt |
| Add cross-task consistency constraints | Ours · OASIS validation | angular error: 24.65 -> 23.89 | Helped |
Closest papers by meaning
- On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness (NeurIPS 2021 · similarity 0.89)
- Improving robustness against common corruptions by covariate shift adaptation (NeurIPS 2020 · similarity 0.89)
- Does enhanced shape bias improve neural network robustness to common corruptions? (ICLR 2021 · similarity 0.87)
- Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation (ICML 2025 · similarity 0.85)
- Improving robustness to corruptions with multiplicative weight perturbations (NeurIPS 2024 · similarity 0.85)
- Slight Corruption in Pre-training Data Makes Better Diffusion Models (NeurIPS 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.