CRM

Convolutional Reconstruction Model for single-image 3D generation with high-quality textures.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

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

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.

Open SourceSelf HostedOfflineGPU
Intermediate
0.0 (0)

Generates high-resolution textured 3D assets from images or text with separate shape and texture models.

Open SourceSelf HostedOfflineGPU 6GB+
Intermediate
0.0 (0)

Generates explorable, mesh-exportable 3D worlds from text or image prompts via panoramic proxies.

Open SourceSelf HostedOfflineGPU 24GB+
Advanced
0.0 (0)

Roblox's research foundation model that generates 3D shapes from text prompts for game assets.

Open SourceSelf HostedOfflineGPU 16GB+
Intermediate
0.0 (0)

Reconstructs 3D shape, texture, and layout of objects from a single cluttered real-world photo.

Open SourceSelf HostedOfflineGPU
Advanced
0.0 (0)

Reconstructs dense 3D scenes from uncalibrated image collections without known camera poses.

Open SourceSelf HostedOfflineGPU
Intermediate
0.0 (0)
Browse all 3D Model Generation tools