Constrained Injective Mapping Benchmark
Creators
- 1. WASHINGTON UNIVERSITY ST LOUIS
- 2. Adobe Research
- 3. Duke University
- 4. Facebook Reality Labs
- 5. Washington University in St. Louis
Description
We are glad to release the benchmark dataset in our Siggraph Asia 2021 paper Optimizing Global Injectivity for Constrained Parameterization. The dataset is used to test various methods on their ability to recover an injective mapping from a non-injective initial mapping while keeping a group of positional constraints in place. The dataset includes 1791 triangle mesh examples. Each example consists of an input rest mesh, an initial mesh, several constrained vertices (called handles), and a ground truth injective mapping obtained from the Locally Injective Mappings Benchmark.
For reference, we also share our method's results on the examples in Constrained-Injective-Mappings-Result.zip.
We hope that our dataset offers a benchmark for future research in this area.
Files
Constrained-Injective-Mappings-Dataset.zip
Files
(3.5 GB)
Name | Size | Download all |
---|---|---|
md5:ef97ca318cc5afa5494387c66fab03aa
|
2.6 GB | Preview Download |
md5:03ee166b490a8c14fa96b11ebc14708e
|
860.7 MB | Preview Download |