Pinned Loading

1. MultiMAE MultiMAE Public

   MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022

   Python 636 75

2. omnidata omnidata Public

   A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

   Jupyter Notebook 491 54

3. XTConsistency XTConsistency Public

   Robust Learning Through Cross-Task Consistency [Best Paper Award Nominee, CVPR2020]

   Python 183 15

4. 3DCommonCorruptions 3DCommonCorruptions Public

   3D Common Corruptions and Data Augmentation, CVPR 2022 [Oral]

   Python 88 10

5. fm-vision-evals fm-vision-evals Public

   How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks, ICLR 2026

   Jupyter Notebook 72 8

6. ViPer ViPer Public

   Python 71 4