A feed-forward stylization network trained with test-time optimization uses correspondence matching and depth losses to produce multi-view consistent stylization that supports downstream SLAM and reconstruction.
Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields
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
-
3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation
A feed-forward stylization network trained with test-time optimization uses correspondence matching and depth losses to produce multi-view consistent stylization that supports downstream SLAM and reconstruction.