Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mei, Zhiting, Shorinwa, Ola, Majumdar, Anirudha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916987433648128
author Mei, Zhiting
Shorinwa, Ola
Majumdar, Anirudha
author_facet Mei, Zhiting
Shorinwa, Ola
Majumdar, Anirudha
contents Semantic distillation in radiance fields has spurred significant advances in open-vocabulary robot policies, e.g., in manipulation and navigation, founded on pretrained semantics from large vision models. While prior work has demonstrated the effectiveness of visual-only semantic features (e.g., DINO and CLIP) in Gaussian Splatting and neural radiance fields, the potential benefit of geometry-grounding in distilled fields remains an open question. In principle, visual-geometry features seem very promising for spatial tasks such as pose estimation, prompting the question: Do geometry-grounded semantic features offer an edge in distilled fields? Specifically, we ask three critical questions: First, does spatial-grounding produce higher-fidelity geometry-aware semantic features? We find that image features from geometry-grounded backbones contain finer structural details compared to their counterparts. Secondly, does geometry-grounding improve semantic object localization? We observe no significant difference in this task. Thirdly, does geometry-grounding enable higher-accuracy radiance field inversion? Given the limitations of prior work and their lack of semantics integration, we propose a novel framework SPINE for inverting radiance fields without an initial guess, consisting of two core components: coarse inversion using distilled semantics, and fine inversion using photometric-based optimization. Surprisingly, we find that the pose estimation accuracy decreases with geometry-grounded features. Our results suggest that visual-only features offer greater versatility for a broader range of downstream tasks, although geometry-grounded features contain more geometric detail. Notably, our findings underscore the necessity of future research on effective strategies for geometry-grounding that augment the versatility and performance of pretrained semantic features.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03104
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields
Mei, Zhiting
Shorinwa, Ola
Majumdar, Anirudha
Computer Vision and Pattern Recognition
Robotics
Semantic distillation in radiance fields has spurred significant advances in open-vocabulary robot policies, e.g., in manipulation and navigation, founded on pretrained semantics from large vision models. While prior work has demonstrated the effectiveness of visual-only semantic features (e.g., DINO and CLIP) in Gaussian Splatting and neural radiance fields, the potential benefit of geometry-grounding in distilled fields remains an open question. In principle, visual-geometry features seem very promising for spatial tasks such as pose estimation, prompting the question: Do geometry-grounded semantic features offer an edge in distilled fields? Specifically, we ask three critical questions: First, does spatial-grounding produce higher-fidelity geometry-aware semantic features? We find that image features from geometry-grounded backbones contain finer structural details compared to their counterparts. Secondly, does geometry-grounding improve semantic object localization? We observe no significant difference in this task. Thirdly, does geometry-grounding enable higher-accuracy radiance field inversion? Given the limitations of prior work and their lack of semantics integration, we propose a novel framework SPINE for inverting radiance fields without an initial guess, consisting of two core components: coarse inversion using distilled semantics, and fine inversion using photometric-based optimization. Surprisingly, we find that the pose estimation accuracy decreases with geometry-grounded features. Our results suggest that visual-only features offer greater versatility for a broader range of downstream tasks, although geometry-grounded features contain more geometric detail. Notably, our findings underscore the necessity of future research on effective strategies for geometry-grounding that augment the versatility and performance of pretrained semantic features.
title Geometry Meets Vision: Revisiting Pretrained Semantics in Distilled Fields
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2510.03104