In synchronized multi-view dynamic scenes, efficient retrospective novel view synthesis is achieved with 3D Gaussian Splatting by propagating optimized Gaussians from an initial SfM point cloud without temporal deformation constraints, supported by a new Blender-based benchmark dataset framework.
Neural radiance fields for the real world: A survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
FSTM improves indoor reconstruction by training geometry first without semantic supervision, then adding semantics, achieving 2.3x faster training and higher object surface recall than joint optimization.
citing papers explorer
-
3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark
In synchronized multi-view dynamic scenes, efficient retrospective novel view synthesis is achieved with 3D Gaussian Splatting by propagating optimized Gaussians from an initial SfM point cloud without temporal deformation constraints, supported by a new Blender-based benchmark dataset framework.
-
First Shape, Then Meaning: Efficient Geometry and Semantics Learning for Indoor Reconstruction
FSTM improves indoor reconstruction by training geometry first without semantic supervision, then adding semantics, achieving 2.3x faster training and higher object surface recall than joint optimization.