Summary of Virtually Enriched Nyu Depth V2 Dataset For Monocular Depth Estimation: Do We Need Artificial Augmentation?, by Dmitry Ignatov et al.
Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?
by Dmitry Ignatov, Andrey Ignatov, Radu Timofte
First submitted to arxiv on: 15 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents ANYU, a new dataset for monocular depth estimation that combines real-world images from the NYU depth v2 dataset with virtually generated objects. Unlike traditional approaches, ANYU doesn’t match virtual objects to specific locations in real-world images; instead, it randomizes rendering parameters like texture, location, and lighting to increase diversity. The authors show that using this dataset can improve monocular depth estimation performance and generalization for different architectures of deep neural networks, particularly the VPD model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ANYU is a new kind of dataset that helps machines learn about distances from just looking at images. It combines real-world pictures with fake objects created in virtual reality. Instead of matching these virtual objects to specific places in the real world, ANYU randomizes things like texture and lighting to create lots of different scenarios. This approach can help machines better estimate distances from just seeing an image. |
Keywords
» Artificial intelligence » Depth estimation » Generalization
