Is This 3D Asset Usable? Beyond the Beauty Render for Asset Curation
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Project page: https://rbz-99.github.io/is-this-3d-asset-usable
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large 3D repositories make it easy to collect assets, but difficult to determine whether they can be reused reliably across scene assembly, editing, rendering, game production…
Abstract
Large 3D repositories make it easy to collect assets, but difficult to determine whether they can be reused reliably across scene assembly, editing, rendering, game production, and training-data construction. An asset can look plausible in RGB while hiding disconnected geometry, problematic UV organization, or materials that fail to resolve correctly after import. We introduce Diagnostic Rendered Evidence (DRE): aligned beauty, wireframe, and UV-seam-plus-wireframe views scored by pass-specific frozen ViT classifiers and combined through late fusion. On 1,234 human labeled TexVerse assets, nested grouped evaluation achieves 86.36% balanced accuracy and 88.32% bad-asset recall. On a separate, balanced 764 external reference test, DRE achieved 88.9% balanced reference-label accuracy. Our method requires only an imported asset and renderer-derived evidence, without repository identity, creator, popularity, text, or source metadata at inference. Our results support cross-corpus portability and show that purpose built diagnostic views expose defects that just the beauty views can miss. Webpage: https://rbz-99.github.io/is-this-3d-asset-usable/
Sources
- MeshFleet: Filtered and Annotated 3D Vehicle Dataset for Domain Specific Generative Modeling
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
- ShapeNet: An Information-Rich 3D Model Repository
- 3D Arena: An Open Platform for Generative 3D Evaluation
- Subjective and Objective Visual Quality Assessment of Textured 3D Meshes
- T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation
- Textured Mesh Quality Assessment: Large-Scale Dataset and Deep Learning-based Quality Metric
- TEXTure: Text-Guided Texturing of 3D Shapes
- Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
- GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark
- PartUV: Part-Based UV Unwrapping of 3D Meshes
- PBR3DGen: A VLM-guided Mesh Generation with High-quality PBR Texture
- Textured mesh Quality Assessment using Geometry and Color Field Similarity
- TexVerse: A Universe of 3D Objects with High-Resolution Textures
- Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation
- Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs