Skip to content
Preprint

NormLift: From Lifted Features To Semantic Reliability In 3D Gaussian Splatting

Sep 2026 · 2 citations · 36 references
Computer Science

TL;DR

Experiments on open-vocabulary 3D semantic segmentation show that NormLift is an efficient, training-free framework that achieves strong performance across evaluation protocols.

Abstract

Training-free weighted aggregation is widely used to lift 2D semantic features onto 3D Gaussians for open-vocabulary scene understanding, yet its theoretical role remains insufficiently understood. Existing analyses typically justify this operation from the rendering side, treating Gaussian features as linearly composable Euclidean variables for reconstructing 2D feature maps. However, this view does not match downstream 3D usage, where each Gaussian is often queried independently in a cosine-based embedding space. We revisit feature lifting from the 3D side and formulate per-Gaussian assignment as a cosine alignment problem on the CLIP unit sphere. Under this objective, the $\ell_2$-normalized semantic back-projected feature emerges as the closed-form solution, providing a complementary interpretation of the standard lifting rule from the perspective of per-Gaussian semantic assignment. This solution is still a convex combination of the observed directions, so every lifted feature is inherently a mixture. Such mixing is unavoidable for any per-Gaussian estimator, and the question is whether it can be measured. The same formulation answers this: the norm of the back-projected feature decomposes into intra-view and inter-view consistency, so the feature magnitude quantifies how mixed the observations are and serves as a semantic reliability signal. Calibrated by effective multi-view support, this reliability score identifies the Gaussians whose lifted direction has drifted and guides a mode-voting refinement that corrects them by copying a single observed CLIP direction instead of averaging. Experiments on open-vocabulary 3D semantic segmentation show that NormLift is an efficient, training-free framework that achieves strong performance across evaluation protocols. Our code is available at https://github.com/kaust-violab/NormLift_release

View source

Similar papers

Preprint Oct 2026

ClunoGS: Compact Language 3D Gaussian Splatting via Unified Optimization

This work proposes ClunoGS, a compact framework for Language 3DGS that combines semantics-aware Gaussian sparsification and vector quantization in a unified constrained objective and shows that jointly coordinating sparsification and quantization better preserves semantic accuracy than applying them independently.

Jian Xu, Yi Li, Ying Huang et al. · 0 citations
Preprint Sep 2026

DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians

Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation models into 3D representations. However, existing referring fields embed language features in a globally view-invariant space, making them fundamentally unable to resolve...

Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran · 0 citations
Preprint Oct 2026

Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error

The same Gaussian of a 3D Gaussian Splatting model is seen from many views, and these views do not always agree on the class it belongs to. The Gaussian may be occluded in some of them, and the confidence of the detector is not the same from one view to another. The ground truth, on the other hand, is given as an annot...

Iván Verdugo Guerra, Ezequiel López Rubio, Jorge García González · 0 citations
#artificial intelligence Preprint Oct 2026

Revisiting Triplet Contrastive Learning for 3D Shape Understanding

In multi-modal 3D pre-training, aligning 3D shapes, their 2D image counterparts, and language descriptions has made tremendous progress. However, we find that supervision from rendered images is unreliable, the semantics encoded in synthetic views are distorted due to domain gap, self-occlusion, and rendering artifacts...

Chao-Yang Zhu, Zhe Liao, Jia-Yi Zhang et al. · 0 citations
Open access Sep 2026

Compressing 3D Gaussian Splatting via Cross-Representation Priors

3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis but incurs high storage and transmission costs due to dense Gaussian primitives. Recent anchor-based compression reduces per-primitive redundancy, yet redundancy across anchors remains largely unexploited. We propose CRP-GS (Cross-Representation Pri...

Ye-Zheng Zhang, Huan-Xiong Liang, Chu-Qin Zhou et al. · 0 citations
Preprint Oct 2026

Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation

Recent feed-forward 3D Gaussian Splatting (3DGS) methods have enabled effective multi-view 3D reconstruction by predicting Gaussian primitives in a single forward pass. However, existing approaches predominantly adopt a pixel-aligned paradigm that predicts one Gaussian per input pixel, coupling the Gaussian count to th...

Sheng Ye, Jiang-Ke Lin, Fu-Dong Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.