FR3D predicts a persistent 3D latent representation for future dynamic reconstruction by explicitly disentangling scene evolution from agent trajectory and using foundation-model distillation.
Vfmf: World modeling by forecasting vision foundation model features
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
FR3D predicts a persistent 3D latent representation for future dynamic reconstruction by explicitly disentangling scene evolution from agent trajectory and using foundation-model distillation.