{"ID":2839859,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14149","arxiv_id":"2511.14149","title":"iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion","abstract":"Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \\textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T\\\u0026T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian","short_abstract":"Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \\textit{render-compare-refine} loop, wher...","url_abs":"https://arxiv.org/abs/2511.14149","url_pdf":"https://arxiv.org/pdf/2511.14149v1","authors":"[\"Hao Wang\",\"Linqing Zhao\",\"Xiuwei Xu\",\"Jiwen Lu\",\"Haibin Yan\"]","published":"2025-11-18T05:22:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606925,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2839859,"paper_url":"https://arxiv.org/abs/2511.14149","paper_title":"iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion","repo_url":"https://github.com/pythongod-exe/iGaussian","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}