Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tao, Yuwen, Zhou, Kanglei, Tan, Xin, Xie, Yuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908901650202624
author Tao, Yuwen
Zhou, Kanglei
Tan, Xin
Xie, Yuan
author_facet Tao, Yuwen
Zhou, Kanglei
Tan, Xin
Xie, Yuan
contents Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions across views. We propose CaRF (Camera-aware Referring Field), a camera-aware cross-view alignment framework for view-consistent referring in 3D Gaussian splatting. CaRF introduces Camera-conditioned Alignment Modulation (CAM) to inject camera geometry into Gaussian-text interactions, and Gaussian-level Cross-view Logit Alignment (GCLA) to explicitly align referring responses of the same Gaussians across calibrated views during training. By turning cross-view discrepancy into an optimizable objective, CaRF enables geometry-aware and view-consistent reasoning directly in the Gaussian space. Extensive experiments on three benchmarks demonstrate that CaRF achieves state-of-the-art performance, improving mIoU by 16.8%, 4.3%, and 2.0% on Ref-LERF, LERF-OVS, and 3D-OVS, respectively. Our code is available at https://github.com/eR3R3/CaRF.
format Preprint
id arxiv_https___arxiv_org_abs_2511_03992
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation
Tao, Yuwen
Zhou, Kanglei
Tan, Xin
Xie, Yuan
Computer Vision and Pattern Recognition
Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions across views. We propose CaRF (Camera-aware Referring Field), a camera-aware cross-view alignment framework for view-consistent referring in 3D Gaussian splatting. CaRF introduces Camera-conditioned Alignment Modulation (CAM) to inject camera geometry into Gaussian-text interactions, and Gaussian-level Cross-view Logit Alignment (GCLA) to explicitly align referring responses of the same Gaussians across calibrated views during training. By turning cross-view discrepancy into an optimizable objective, CaRF enables geometry-aware and view-consistent reasoning directly in the Gaussian space. Extensive experiments on three benchmarks demonstrate that CaRF achieves state-of-the-art performance, improving mIoU by 16.8%, 4.3%, and 2.0% on Ref-LERF, LERF-OVS, and 3D-OVS, respectively. Our code is available at https://github.com/eR3R3/CaRF.
title Camera-Aware Cross-View Alignment for Referring 3D Gaussian Splatting Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.03992