# Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach

arXiv: https://arxiv.org/abs/2605.14601 · HTML: https://mlsanity.com/paper/2605.14601/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 10 of 10)

- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://mlsanity.com/paper/2002.12212/) (2020)
- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://mlsanity.com/paper/2103.06422/) (2021)
- [Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360deg Panoramic Imagery](https://mlsanity.com/paper/1808.06253/) (2018)
- [DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization](https://mlsanity.com/paper/2108.10743/) (2021)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [One Flight Over the Gap: A Survey from Perspective to Panoramic Vision](https://mlsanity.com/paper/2509.04444/) (2025)
- [PanoContext-Former: Panoramic Total Scene Understanding with a Transformer](https://mlsanity.com/paper/2305.12497/) (2023)
- [3D Object Detection from a Single Fisheye Image Without a Single Fisheye Training Image](https://mlsanity.com/paper/2003.03759/) (2020)

## Abstract (arXiv)

Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit representation efficiency. To overcome this limitation, this paper proposes PanoGSDet, a monocular panoramic 3D detection framework built upon continuous semantic 3D Gaussian representations. The proposed framework comprises a panoramic depth estimation component and a semantic Gaussian component. The panoramic depth estimation component extracts the equirectangular semantic and depth features from the monocular panorama input. The semantic Gaussian component includes a semantic Gaussian lifting module that projects spherical features into 3D semantic Gaussians, a semantic Gaussian optimization module that refines these semantic Gaussians, and a Gaussian guided prediction head that generates 3D bounding boxes from optimized Gaussian representations. Extensive experiments on the Structured3D dataset demonstrate that our method significantly outperforms existing methods.