CVJul 17, 2024

LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generation

arXiv:2407.12356v111 citationsh-index: 17
Originality Incremental advance
AI Analysis

This addresses the need for better evaluation metrics in layout generation tasks, particularly for researchers and practitioners dealing with diverse layouts, though it is incremental as it builds on optimal transport for a specific domain.

The authors tackled the problem of evaluating layout generation by proposing a new similarity measure based on optimal transport, which handles layout differences more flexibly than existing methods; empirical results show it offers more reliable comparisons than FID and Max.IoU for tasks like unconditional layout generation.

We introduce a layout similarity measure designed to evaluate the results of layout generation. While several similarity measures have been proposed in prior research, there has been a lack of comprehensive discussion about their behaviors. Our research uncovers that the majority of these measures are unable to handle various layout differences, primarily due to their dependencies on strict element matching, that is one-by-one matching of elements within the same category. To overcome this limitation, we propose a new similarity measure based on optimal transport, which facilitates a more flexible matching of elements. This approach allows us to quantify the similarity between any two layouts even those sharing no element categories, making our measure highly applicable to a wide range of layout generation tasks. For tasks such as unconditional layout generation, where FID is commonly used, we also extend our measure to deal with collection-level similarities between groups of layouts. The empirical result suggests that our collection-level measure offers more reliable comparisons than existing ones like FID and Max.IoU.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes