RECORD
Hole-robust Wireframe Detection
Computer Vision and Pattern Recognition · Submitted 30 Nov 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We show qualitatively and quantitatively that our approach significantly outperforms previous works unable to handle holes, as well as improves ordinary detection without holes given.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
"Wireframe" is a line segment based representation designed to well capture large-scale visual properties of regular, structural shaped man-made scenes surrounding us. Unlike the wireframes, conventional edges or line segments focus on all visible edges and lines without particularly distinguishing which of them are more salient to man-made structural information. Existing wireframe detection models rely on supervising the annotated data but do not explicitly pay attention to understand how to compose the structural shapes of the scene. In addition, we often face that many foreground objects occluding the background scene interfere with proper inference of the full scene structure behind them. To resolve these problems, we first time in the field, propose new conditional data generation and training that help the model understand how to ignore occlusion indicated by holes, such as foreground object regions masked out on the image. In addition, we first time combine GAN in the model to let the model better predict underlying scene structure even beyond large holes. We also introduce pseudo labeling to further enlarge the model capacity to overcome small-scale labeled data. We show qualitatively and quantitatively that our approach significantly outperforms previous works unable to handle holes, as well as improves ordinary detection without holes given.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | "Wireframe" is a line segment based representation designed to well capture large-scale visual properties of regular, structural shaped man-made scenes surrounding us. | background 1.00 | 0.08 | 0.02 | asserted 1.00 |
| s1 | Unlike the wireframes, conventional edges or line segments focus on all visible edges and lines without particularly distinguishing which of them are more salient to man-made structural information. | background 0.95 | 0.06 | 0.02 | asserted 1.00 |
| s2 | Existing wireframe detection models rely on supervising the annotated data but do not explicitly pay attention to understand how to compose the structural shapes of the scene. | gap 0.67 | 0.04 | 0.03 | asserted 1.00 |
| s3 | In addition, we often face that many foreground objects occluding the background scene interfere with proper inference of the full scene structure behind them. | background 0.93 | 0.11 | 0.02 | asserted 0.94 |
| s4 | To resolve these problems, we first time in the field, propose new conditional data generation and training that help the model understand how to ignore occlusion indicated by holes, such as foreground object regions masked out on the image. | contribution 0.67 | 0.92 | 0.08 | asserted 0.99 |
| s5 | In addition, we first time combine GAN in the model to let the model better predict underlying scene structure even beyond large holes. | method 0.54 | 0.93 | 0.05 | asserted 0.94 |
| s6 | We also introduce pseudo labeling to further enlarge the model capacity to overcome small-scale labeled data. | method 0.73 | 0.93 | 0.04 | asserted 0.96 |
| s7 | We show qualitatively and quantitatively that our approach significantly outperforms previous works unable to handle holes, as well as improves ordinary detection without holes given. | result 1.00 | 0.96 | 0.89 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
"Wireframe" is a line segment based representation designed to well capture large-scale visual properties of regular, structural shaped man-made scenes surrounding us. Unlike the wireframes, conventional edges or line segments focus on all visible edges and lines without particularly distinguishing which of them are more salient to man-made structural information. Existing wireframe detection models rely on supervising the annotated data but do not explicitly pay attention to understand how to compose the structural shapes of the scene. In addition, we often face that many foreground objects occluding the background scene interfere with proper inference of the full scene structure behind them. To resolve these problems, we first time in the field, propose new conditional data generation and training that help the model understand how to ignore occlusion indicated by holes, such as foreground object regions masked out on the image. In addition, we first time combine GAN in the model to let the model better predict underlying scene structure even beyond large holes. We also introduce pseudo labeling to further enlarge the model capacity to overcome small-scale labeled data. We show qualitatively and quantitatively that our approach significantly outperforms previous works unable to handle holes, as well as improves ordinary detection without holes given.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.