TIBR4D: Tracing-Guided Iterative Boundary Refinement for Efficient 4D Gaussian Segmentation
This work addresses the problem of segmenting objects in dynamic 4D scenes for applications like computer vision and graphics, offering an incremental improvement over existing methods.
The paper tackles object-level segmentation in dynamic 4D Gaussian scenes by proposing TIBR4D, a learning-free framework that uses iterative boundary refinement to lift video masks to 4D spaces, resulting in more accurate object point clouds with clearer boundaries and higher efficiency compared to state-of-the-art methods.
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.