Paper

Splat Feature Solver

Feng, Andrew, Liu, Rong, Chen, Meida, Xiong, Butian, Xu, Kenneth

2026

Overview

Feature lifting has emerged as a crucial component in 3D scene understanding, enabling the attachment of rich image feature descriptors (e.g., DINO, CLIP) onto splat-based 3D representations. The core challenge lies in optimally assigning rich general attributes to 3D primitives while addressing the inconsistency issues from multi-view images. We present a unified, kernel- and feature-agnostic formulation of the feature lifting problem as a sparse linear inverse problem, which can be solved efficiently in closed form. Our approach admits a provable upper bound on the global optimal error under convex losses for delivering high quality lifted features. To address inconsistencies and noise in multi-view observations, we introduce two complementary regularization strategies to stabilize the solution and enhance semantic fidelity. Tikhonov Guidance enforces numerical stability through soft diagonal dominance, while Post-Lifting Aggregation filters noisy inputs via feature clustering. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on open-vocabulary 3D segmentation benchmarks, outperforming training-based, grouping-based, and heuristic-forward baselines while producing lifted features in minutes. Our \\textbf{code} is available in the \\href{https://github.com/saliteta/splat-distiller/tree/main}{\\textcolor{blue}{GitHub}}. We provide additional \\href{https://splat-distiller.pages.dev/}{\\textcolor{blue}{website}} for more visualization, as well as the \\href{https://www.youtube.com/watch?v=CH-G5hbvArM}{\\textcolor{blue}{video}}.

• Publisher: Cornell University Library, arXiv.org
• Subject: Clustering / Hoisting / Inverse problems / Numerical stability / Optimization / Regularization / Scene analysis / Upper bounds