SemDynReg constructs per-object ID maps from SAM and image features to regularize position, scale, and rotation of top-k Gaussians per object in dynamic 3DGS.
Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Ground4D reconstructs dynamic 4D scenes from monocular video by initializing dynamic Gaussians from VGGT geometry and refining them with multi-view depth consistency at observed and virtual viewpoints.
citing papers explorer
-
SemDynReg: Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting
SemDynReg constructs per-object ID maps from SAM and image features to regularize position, scale, and rotation of top-k Gaussians per object in dynamic 3DGS.
-
Ground4D: Consistency-Aware 4D Reconstruction from Monocular Video
Ground4D reconstructs dynamic 4D scenes from monocular video by initializing dynamic Gaussians from VGGT geometry and refining them with multi-view depth consistency at observed and virtual viewpoints.