8,320 data samples of uniformly distributed points and their signed distance function (SDF) values. The subset contains three shape classes: airplanes (2156 samples), chairs (4189 samples), and sofas (1975 samples). It was created by AlexWolski and last updated on November 30, 2022.
Use Cases
- Train generative models for 3D shapes based on SDF point cloud data.
- Benchmark shape reconstruction algorithms using uniform point samples.
- Analyze geometric properties of specific object classes like airplanes, chairs, and sofas.
- Develop methods for converting point clouds with SDF values into 3D meshes.
Strengths
- Contains 8,320 data samples, providing a substantial collection.
- Each sample includes 200,000 uniformly distributed points, offering high spatial detail.
- Focuses on three distinct shape classes: airplanes, chairs, and sofas.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Last updated 2022-11-30 12:08:06; freshness should be verified.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- ShapeGan Project subset of ShapeNet SDF Dataset.
- Freshness
- 2022-11-30 12:08:06