XNews

NVIDIA Introduces Axolotl3D for 3D Generation

NVIDIA Introduces Axolotl3D for 3D Generation

NVIDIA research presented Axolotl3D at ECCV 2026, a multimodal and occlusion-aware 3D generation model. It combines images, camera data, and partial geometry to reconstruct missing regions while preserving observed ones, achieving state-of-the-art results.

Key insights

Model Capabilities

Axolotl3D is a multimodal and occlusion-aware 3D generation model. It combines images, camera data, and partial geometry to reconstruct missing regions while preserving observed ones. It achieves state-of-the-art results across single- and multi-view settings.

Source posts