light0626/TempoVista

TempoVista

The source code and Dyn-3D benchmark are available at InkMind-AI/Dyn-3D.

Citation

If you use the TempoVista models or the Dyn-3D benchmark, please cite:

@misc{tempovista2026,
  title  = {Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models},
  author = {Anonymous Authors},
  year   = {2026},
  note   = {Under review}
}