PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views

• URL: http://arxiv.org/abs/2606.27071v1
• Date: Thu, 25 Jun 2026 14:15:09 GMT
• Title: PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views
• Abstract summary: PanoImager is an SfM-free framework that combines feed-forward pose/depth priors, geometry-conditioned diffusion view completion, and depth-guided 3DGS optimization.<n>We show improved stability under extreme sparsity, suggesting PanoImager as an offline/background component for map refinement when SfM/SLAM fails to initialize.
• Score: 3.5844726281072448
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Panoramic sensing offers wide field-of-view coverage, yet 3D reconstruction from sparse panoramas remains challenging under rotation-dominant, weak-parallax motion. In such regimes, SfM/SLAM initialization is often ill-conditioned and unreliable. We present PanoImager, an SfM-free framework that combines feed-forward pose/depth priors, geometry-conditioned diffusion view completion, and depth-guided 3DGS optimization. Given only a few panoramic images, PanoImager decomposes them into local perspective views, synthesizes auxiliary observations to enrich sparse evidence, and stabilizes Gaussian optimization for improved cross-view consistency. Experiments on multiple benchmarks show improved stability under extreme sparsity, suggesting PanoImager as an offline/background component for map refinement when SfM/SLAM fails to initialize.

Related papers

• PanoGS-SLAM: Panoramic 3D Gaussian Splatting SLAM [20.25032556921585]
  We present PanoGS-SLAM, the first panoramic dense SLAM system built on 3D Gaussian Splatting.<n>Our method per- forms differentiable rendering and pose optimization directly in the spherical domain.<n>Experiments show that PanoGS-SLAM consistently outperforms geometric and GS-based baselines in tracking accuracy and rendering quality.
  arXiv  Detail & Related papers  (2026-09-15T16:26:12Z)
• FastPano3D: Feed-Forward Indoor Panoramic 3D Reconstruction from a Single Image [5.543213546428594]
  FastPano3D is an end-to-end framework that directly generates renderable 3D Gaussian representations from a single panoramic image.<n>Our approach reconstructs high-fidelity 3D scenes within seconds, achieving up to 156 times faster inference than prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-06-29T14:23:12Z)
• PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery [41.23812453847979]
  PanoVGGT jointly predicts camera poses, depth maps, and 3D point clouds from one or multiple panoramas in a single forward pass.<n>In addition, we contribute PanoCity, a large-scale outdoor panoramic dataset with dense depth and 6-DoF pose annotations.
  arXiv  Detail & Related papers  (2026-03-18T10:24:06Z)
• CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis [53.231427733457224]
  CylinderSplat is a feed-forward framework for panoramic 3DGS.<n>It achieves state-of-the-art results in both single-view and multi-view panoramic novel view synthesis.
  arXiv  Detail & Related papers  (2026-03-06T04:04:20Z)
• MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild [47.52462219920857]
  In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances.<n>We present MS-GS, a novel framework designed with Multi-appearance capabilities in Sparse-view scenarios using 3DGS.<n>We demonstrate that MS-GS achieves photorealistic renderings under various challenging sparse-view and multi-appearance conditions.
  arXiv  Detail & Related papers  (2025-09-19T03:06:49Z)
• You Need a Transition Plane: Bridging Continuous Panoramic 3D Reconstruction with Perspective Gaussian Splatting [57.44295803750027]
  We present a novel framework, named TPGS, to bridge continuous panoramic 3D scene reconstruction with perspective Gaussian splatting.<n>Specifically, we optimize 3D Gaussians within individual cube faces and then fine-tune them in the stitched panoramic space.<n>Experiments on indoor and outdoor, egocentric, and roaming benchmark datasets demonstrate that our approach outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-12T03:42:50Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)
• PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas [54.4948540627471]
  We propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas. Unlike generalizable radiance fields trained on perspective images, PanoGRF avoids the information loss from panorama-to-perspective conversion. Results on multiple panoramic datasets demonstrate that PanoGRF significantly outperforms state-of-the-art generalizable view synthesis methods.
  arXiv  Detail & Related papers  (2023-06-02T13:35:07Z)
• Enhanced Stable View Synthesis [86.69338893753886]
  We introduce an approach to enhance the novel view synthesis from images taken from a freely moving camera. The introduced approach focuses on outdoor scenes where recovering accurate geometric scaffold and camera pose is challenging.
  arXiv  Detail & Related papers  (2023-03-30T01:53:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.