CRM
Convolutional Reconstruction Model for single-image 3D generation with high-quality textures.
About
CRM, the Convolutional Reconstruction Model from THU-ML, is a feed-forward model that turns a single image into a textured 3D mesh in about ten seconds. It generates six-view images and corresponding canonical coordinate maps, then reconstructs geometry with a convolutional network, outputting an OBJ model. Inputs work best preprocessed onto a grey background. Released as open-source research code.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- 3D Model Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
CUDA-accelerated Gaussian splatting rasterization library with Python bindings from the Nerfstudio team.
Generates high-resolution textured 3D assets from images or text with separate shape and texture models.
Generates explorable, mesh-exportable 3D worlds from text or image prompts via panoramic proxies.
Roblox's research foundation model that generates 3D shapes from text prompts for game assets.
Reconstructs 3D shape, texture, and layout of objects from a single cluttered real-world photo.
Reconstructs dense 3D scenes from uncalibrated image collections without known camera poses.