# PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World

arXiv: https://arxiv.org/abs/2605.13169 · HTML: https://mlsanity.com/paper/2605.13169/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 59 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 30 of 50)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning](https://mlsanity.com/paper/2504.08837/) (2025)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning](https://mlsanity.com/paper/2505.15966/) (2025)
- [LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness](https://mlsanity.com/paper/2409.18125/) (2024)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [Cambrian-S: Towards Spatial Supersensing in Video](https://mlsanity.com/paper/2511.04670/) (2025)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [GridMM: Grid Memory Map for Vision-and-Language Navigation](https://mlsanity.com/paper/2307.12907/) (2023)
- [StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling](https://mlsanity.com/paper/2507.05240/) (2025)
- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videos](https://mlsanity.com/paper/2110.05122/) (2021)
- [Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2204.09667/) (2022)
- [DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation](https://mlsanity.com/paper/2308.07498/) (2023)
- [How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM](https://mlsanity.com/paper/2504.05786/) (2025)
- [Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation](https://mlsanity.com/paper/2406.12849/) (2024)
- [360+x: A Panoptic Multi-modal Scene Understanding Dataset](https://mlsanity.com/paper/2404.00989/) (2024)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation](https://mlsanity.com/paper/2503.07098/) (2025)
- [OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer](https://mlsanity.com/paper/2302.03453/) (2023)
- [One Flight Over the Gap: A Survey from Perspective to Panoramic Vision](https://mlsanity.com/paper/2509.04444/) (2025)
- [DA2: Depth Anything in Any Direction](https://mlsanity.com/paper/2509.26618/) (2025)
- [Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation](https://mlsanity.com/paper/2512.16913/) (2025)

## Built on by (most cited first, 5 of 5)

- [SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation](https://mlsanity.com/paper/2607.01766/) (2026)
- [EAGOR: Embodied Reasoning in Omni-direction](https://mlsanity.com/paper/2607.06165/) (2026)
- [UniSHARP: Universal Sharp Monocular View Synthesis](https://mlsanity.com/paper/2606.07514/) (2026)
- [Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation](https://mlsanity.com/paper/2607.26646/) (2026)
- [OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning](https://mlsanity.com/paper/2606.30378/) (2026)

## Abstract (arXiv)

Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation, robotic search, and 3D scene understanding, 360-degree panoramic sensing offers a form of supersensing by capturing the entire surrounding environment at once. However, existing MLLM pipelines typically decompose panoramas into multiple perspective views, leaving the spherical structure of equirectangular projection (ERP) largely implicit. In this paper, we study pano-native understanding, which requires an MLLM to reason over an ERP panorama as a continuous, observer-centered space. To this end, we first define the key abilities for pano-native understanding, including semantic anchoring, spherical localization, reference-frame transformation, and depth-aware 3D spatial reasoning. We then build a large-scale metadata construction pipeline that converts mixed-source ERP panoramas into geometry-aware, language-grounded, and depth-aware supervision, and instantiate these signals as capability-aligned instruction tuning data. On the model side, we introduce PanoWorld with Spherical Spatial Cross-Attention, which injects spherical geometry into the visual stream. We further construct PanoSpace-Bench, a diagnostic benchmark for evaluating ERP-native spatial reasoning. Experiments show that PanoWorld substantially outperforms both proprietary and open-source baselines on PanoSpace-Bench, H* Bench, and R2R-CE Val-Unseen benchmarks. These results demonstrate that robust panoramic reasoning requires dedicated pano-native supervision and geometry-aware model adaptation. All source code and proposed data will be publicly released.