TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation

TL;DR

TIBR4D introduces a novel, learning-free 4D Gaussian segmentation framework with iterative boundary refinement, effectively handling occlusions and complex motions for improved object segmentation in dynamic scenes.

Contribution

The paper proposes a two-stage iterative boundary refinement method, TIBR4D, that enhances 4D Gaussian segmentation accuracy without learning, outperforming existing methods in efficiency and boundary clarity.

Findings

Produces more accurate object Gaussian point clouds.

Achieves clearer boundaries and higher efficiency than state-of-the-art methods.

Effectively handles occlusions and complex motions in 4D scenes.

Abstract

Object-level segmentation in dynamic 4D Gaussian scenes remains challenging due to complex motion, occlusions, and ambiguous boundaries. In this paper, we present an efficient learning-free 4D Gaussian segmentation framework that lifts video segmentation masks to 4D spaces, whose core is a two-stage iterative boundary refinement, TIBR4D. The first stage is an Iterative Gaussian Instance Tracing (IGIT) at the temporal segment level. It progressively refines Gaussian-to-instance probabilities through iterative tracing, and extracts corresponding Gaussian point clouds that better handle occlusions and preserve completeness of object structures compared to existing one-shot threshold-based methods. The second stage is a frame-wise Gaussian Rendering Range Control (RCC) via suppressing highly uncertain Gaussians near object boundaries while retaining their core contributions for more accurate boundaries. Furthermore, a temporal segmentation merging strategy is proposed for IGIT to balance identity consistency and dynamic awareness. Longer segments enforce stronger multi-frame constraints for stable identities, while shorter segments allow identity changes to be captured promptly. Experiments on HyperNeRF and Neu3D demonstrate that our method produces accurate object Gaussian point clouds with clearer boundaries and higher efficiency compared to SOTA methods.