RefineSplat reconstructs each object with its own Gaussians for open-vocabulary queries

Yiren Lu et al. present RefineSplat, a reconstruction-guided extension of their earlier Segment-then-Splat framework for open-vocabulary 3D scene understanding. Methods that splat a scene first and add labels afterwards, they argue, often suffer from view inconsistency, ambiguous object boundaries and weak object-level correspondence.
RefineSplat tracks objects in 2D and then reconstructs each one with a dedicated set of 3D Gaussians, keeping an explicit object-to-Gaussian correspondence for unified open-vocabulary segmentation and retrieval. The paper describes further robustness work on top of that object-centric reconstruction.