2025/08/17 by Butian Xiong, Rong Liu, Xiong, Butian +7 · 2 citations
Computer Science · Decision Sciences · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Model-Driven Software Engineering Techniques #Simulation Techniques and Applications
paper · pdf · doi:10.48550/arxiv.2508.12216
openalex publication_date 2025/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 code is available in the \hrefhttps://github.com/saliteta/splat-distiller/tree/main\textcolorblueGitHub. We provide additional \hrefhttps://splat-distiller.pages.dev/\textcolorbluewebsite for more visualization, as well as the \hrefhttps://www.youtube.com/watch?v=CH-G5hbvArM\textcolorbluevideo.