By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.
ACM Transactions on Graphics (ToG) , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.