A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.
360Roam: Real-time indoor roaming using geometry-aware 360◦ radiance fields
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Virtual tour among sparse 360$^\circ$ images is widely used while hindering smooth and immersive roaming experiences. The emergence of Neural Radiance Field (NeRF) has showcased significant progress in synthesizing novel views, unlocking the potential for immersive scene exploration. Nevertheless, previous NeRF works primarily focused on object-centric scenarios, resulting in noticeable performance degradation when applied to outward-facing and large-scale scenes due to limitations in scene parameterization. To achieve seamless and real-time indoor roaming, we propose a novel approach using geometry-aware radiance fields with adaptively assigned local radiance fields. Initially, we employ multiple 360$^\circ$ images of an indoor scene to progressively reconstruct explicit geometry in the form of a probabilistic occupancy map, derived from a global omnidirectional radiance field. Subsequently, we assign local radiance fields through an adaptive divide-and-conquer strategy based on the recovered geometry. By incorporating geometry-aware sampling and decomposition of the global radiance field, our system effectively utilizes positional encoding and compact neural networks to enhance rendering quality and speed. Additionally, the extracted floorplan of the scene aids in providing visual guidance, contributing to a realistic roaming experience. To demonstrate the effectiveness of our system, we curated a diverse dataset of 360$^\circ$ images encompassing various real-life scenes, on which we conducted extensive experiments. Quantitative and qualitative comparisons against baseline approaches illustrated the superior performance of our system in large-scale indoor scene roaming.
fields
cs.CV 5years
2026 5representative citing papers
PanoGaussian distills panoramic representations into explicit dynamic Gaussians for consistent monocular 4D scene synthesis under large viewpoint variations.
UniTriSplat unifies 3D Gaussian Splatting across camera types by performing splatting and optimization on a HEALPix spherical grid with equal-area sampling.
Presents COVER, a greedy ERP viewpoint curator with coverage scoring and depth conflict penalization, and releases the CM-EVS dataset of 36k sparse panoramic RGB-D-pose frames from 1,275 indoor scenes plus outdoor data.
An SfM-free pipeline that turns a few sparse panoramas into a more stable 3D Gaussian map by combining feed-forward pose/depth priors, diffusion view completion, and depth-constrained optimization.
citing papers explorer
-
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.
-
Unified Panoramic-Gaussian Representation for Monocular 4D Scene Synthesis
PanoGaussian distills panoramic representations into explicit dynamic Gaussians for consistent monocular 4D scene synthesis under large viewpoint variations.
-
UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras
UniTriSplat unifies 3D Gaussian Splatting across camera types by performing splatting and optimization on a HEALPix spherical grid with equal-area sampling.
-
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
Presents COVER, a greedy ERP viewpoint curator with coverage scoring and depth conflict penalization, and releases the CM-EVS dataset of 36k sparse panoramic RGB-D-pose frames from 1,275 indoor scenes plus outdoor data.
-
PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views
An SfM-free pipeline that turns a few sparse panoramas into a more stable 3D Gaussian map by combining feed-forward pose/depth priors, diffusion view completion, and depth-constrained optimization.