JustusThies/NeuralTexGen
Image-space texture optimization of 3D meshes using PyTorch
This project helps 3D artists, game developers, or anyone working with 3D models to create high-quality, realistic textures directly from multiple photographs. You provide 3D models of an object or scene, alongside UV mappings and corresponding photographs. The system then generates a cohesive, optimized texture map that accurately reflects the colors and details from your input images.
No commits in the last 6 months.
Use this if you have a 3D model and several photographs of it, and you need to generate a single, high-fidelity texture map without manually painting or complex projection.
Not ideal if you don't have a 3D reconstructed mesh or camera parameters, or if you need to create entirely new textures from scratch rather than optimizing existing visual data.
Stars
73
Forks
11
Language
Python
License
—
Category
Last pushed
Jul 08, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JustusThies/NeuralTexGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model