SHARE: Bridging Shape and Ray Estimation for Pose-Free Generalizable Gaussian Splatting

Youngju Na, Taeyeon Kim, Jumin Lee, Kyu Beom Han, Woo Jae Kim, Sung-eui Yoon

Keywords: 3D Gaussian Splatting, Novel View Synthesis, Pose Estimation

TL;DR: A pose-free Generalizable 3D Gaussian Splatting

Abstract:

While generalizable 3D Gaussian Splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-world scenarios, obtaining accurate poses is challenging, leading to noisy pose estimates and geometric misalignments. To address this, we introduce SHARE, a novel pose-free generalizable Gaussian Splatting framework that overcomes these ambiguities. Our ray-guided multi-view fusion network consolidates multi-view features into a unified pose-aware canonical volume, bridging 3D reconstruction and ray-based pose estimation. In addition, we propose an anchor-aligned Gaussian prediction strategy for fine-grained geometry estimation within a canonical view.
Extensive experiments on diverse real-world datasets show that SHARE achieves state-of-the-art performance in pose-free generalizable Gaussian splatting.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9315