OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
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.
years
2026 4verdicts
UNVERDICTED 4representative citing papers
MemoBench is a new diagnostic benchmark with automated and VQA metrics that evaluates memory consistency in video models under disappear-and-reappear in dynamic environments.
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
UniSHARP performs universal sharp monocular view synthesis by implicit alignment of diverse camera images in a unified omnidirectional latent space using ray-arranged Gaussian primitives and UniK3D-inspired feature decoding.
citing papers explorer
-
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
-
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
MemoBench is a new diagnostic benchmark with automated and VQA metrics that evaluates memory consistency in video models under disappear-and-reappear in dynamic environments.
-
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
SimWorlds presents a multi-agent system with planner-coder-reviewer workflow, layered scene protocol, and runtime inspection tools to create dynamic 4D scenes from text, plus the 4DBuildBench benchmark showing outperformance over baselines.
-
UniSHARP: Universal Sharp Monocular View Synthesis
UniSHARP performs universal sharp monocular view synthesis by implicit alignment of diverse camera images in a unified omnidirectional latent space using ray-arranged Gaussian primitives and UniK3D-inspired feature decoding.