# Dense360: Dense Understanding from Omnidirectional Panoramas

arXiv: https://arxiv.org/abs/2506.14471 · HTML: https://mlsanity.com/paper/2506.14471/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 70 of its 77 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 70)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)

## Built on by (most cited first, 9 of 9)

- [ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?](https://mlsanity.com/paper/2510.11549/) (2025)
- [PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World](https://mlsanity.com/paper/2605.13169/) (2026)
- [Panoramic Affordance Prediction](https://mlsanity.com/paper/2603.15558/) (2026)
- [Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling](https://mlsanity.com/paper/2606.27745/) (2026)
- [EAGLE-360: Embodied Active Global-to-Local Exploration in 360^circ](https://mlsanity.com/paper/2607.02479/) (2026)
- [JoPano: Unified Panorama Generation via Joint Modeling](https://mlsanity.com/paper/2512.06885/) (2025)
- [OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning](https://mlsanity.com/paper/2606.30378/) (2026)
- [Seek to Segment: Active Perception for Panoramic Referring Segmentation](https://mlsanity.com/paper/2607.02497/) (2026)
- [SCCM: Spherically Consistent Coarse Matching for ERP Dense Feature Correspondence](https://mlsanity.com/paper/2609.36545/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world understanding capabilities through limited field-of-view (FOV) visual inputs (e.g., 70 degree), we take the first step toward dense understanding from omnidirectional panoramas. We first introduce an omnidirectional panoramas dataset featuring a comprehensive suite of reliability-scored annotations. Specifically, our dataset contains 160K panoramas with 5M dense entity-level captions, 1M unique referring expressions, and 100K entity-grounded panoramic scene descriptions. Compared to multi-view alternatives, panoramas can provide more complete, compact, and continuous scene representations through equirectangular projections (ERP). However, the use of ERP introduces two key challenges for MLLMs: i) spatial continuity along the circle of latitude, and ii) latitude-dependent variation in information density. We address these challenges through ERP-RoPE, a position encoding scheme specifically designed for panoramic ERP. In addition, we introduce Dense360-Bench, the first benchmark for evaluating MLLMs on omnidirectional captioning and grounding, establishing a comprehensive framework for advancing dense visual-language understanding in panoramic settings.