ComAsset: 83 Canonicalized 3D Object Meshes for Affordance Research

83 object meshes collected from SketchFab for the paper 'Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models'. The dataset was manually canonicalized in terms of location, orientation, and scale and converted to .obj format with image textures. It was created by HyeonwooKim and last updated on March 20, 2025.

Use Cases

• Training models for 3D object affordance discovery based on the canonicalized mesh data.
• Benchmarking algorithms for object canonicalization based on the manually standardized location, orientation, and scale.
• Developing applications that integrate 3D object data with 2D diffusion models based on the dataset's stated purpose.
• Creating synthetic scenes or environments using the collected and categorized 3D object meshes.

Strengths

• Contains 83 distinct object meshes, providing a concrete collection.
• All meshes were manually canonicalized for location, orientation, and scale, suggesting consistency.
• Meshes are converted to .obj format with image texture files, indicating a standardized visual representation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset's size, file formats beyond .obj, and license are unknown.

Provenance

Source

SketchFab

Collection Method

Collected and manually canonicalized.

Freshness

Last updated 2025-03-20 10:55:26; freshness should be verified.