TL;DR
A boundary identification framework based on Gaussian gradient conflict, which analyzes the semantic gradients received by each Gaussian and decomposes them according to their semantic origins, and achieves the best average mIoU among the evaluated methods.
3D Gaussian Splatting (3DGS) enables real-time photorealistic scene reconstruction, yet its segmentation tasks suffer from two critical flaws: poor 3D consistency (e.g., blurred instance boundaries and unstable cross-view semantic association) and insufficient structural awareness near ambiguous object boundaries. To a...
3D Gaussian Splatting (3DGS) has recently gained significant attention as an efficient representation for 3D scene modeling and photo-realistic rendering. However, achieving robust instance-level segmentation within this representation remains challenging due to inter-instance interference, noisy features, and limited...
VCAR, a training-free coarse-to-fine segmentation strategy based on View Completeness and Axis-aware Boundary Refinement, is proposed and Axis-aware Boundary Refinement is introduced to mitigate artifacts from anisotropic primitives.
While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuristics or multi-model ensembles. We introduce SplatLabel, an automated pipeline that leverages a 4D Gaussian representation to extract LiDAR...
PePESeg3D achieves state-of-the-art performance in both multi-scale segmentation and scene reconstruction, highlighting the importance of integrating perception priors into both geometry optimization and feature learning for accurate multi-scale 3D segmentation.
GaussianDS, a depth-supervised semantic 3DGS framework that treats semantic lifting as a supervision-alignment problem and jointly optimizes RGB appearance, rendered depth, and compact semantics from scratch, is proposed.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
