[ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
-
Updated
May 1, 2026 - Python
#
3d-foundation-model
Here are 4 public repositories matching this topic...
VGGT-X: When VGGT Meets Dense Novel View Synthesis
memory-efficient global-alignment 3d-reconstruction novel-view-synthesis 3dgs vggt 3d-foundation-model dense-view
-
Updated
Feb 4, 2026 - Python
Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
image-matching depth-estimation camera-pose-estimation large-language-models vlms 3d-foundation-model object-level-3d
-
Updated
Jun 1, 2026 - Jupyter Notebook
Official Code for "Can These Views Be One Scene?"
colmap novel-view-synthesis robustness-analysis 3d-foundation-model robustness-evaluation sparse-view-3d-reconstruction 3d-consistency 3d-metrics novel-viewpoint
-
Updated
May 22, 2026 - Python
Improve this page
Add a description, image, and links to the 3d-foundation-model topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the 3d-foundation-model topic, visit your repo's landing page and select "manage topics."