RetimeGS enables ghost-free continuous-time rendering of dynamic scenes in 4D Gaussian Splatting by explicitly modeling temporal Gaussian behavior and adding optical flow-guided supervision plus triple-rendering checks.
Streamsplat: Towards online dynamic3dreconstructionfromuncalibratedvideostreams
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
citing papers explorer
-
RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting
RetimeGS enables ghost-free continuous-time rendering of dynamic scenes in 4D Gaussian Splatting by explicitly modeling temporal Gaussian behavior and adding optical flow-guided supervision plus triple-rendering checks.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.