3D Model Generation and Vision Transformers
33 repos
Libraries and tools for converting images to 3D models and working with vision-based deep learning architectures. The cluster centers on transformer-based approaches for 3D reconstruction, leveraging PyTorch and standardized model hub formats (safetensors, model_hub_mixin) for sharing pretrained weights. Key projects explore vector quantization, autoencoder variants, and attention mechanisms adapted for visual-to-spatial generation tasks.
model_hub_mixin ·506
pytorch_model_hub_mixin ·506
safetensors ·506
image-to-3d ·360
en ·299
mapanything ·167
covisibility ·167
camera-pose ·167
computer-vision ·167
3d-reconstruction ·167
