Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method

• URL: http://arxiv.org/abs/2505.14197v1
• Date: Tue, 20 May 2025 10:55:26 GMT
• Title: Towards Omnidirectional Reasoning with 360-R1: A Dataset, Benchmark, and GRPO-based Method
• Authors: Xinshen Zhang, Zhen Ye, Xu Zheng,
• Abstract summary: We introduce OmniVQA, the first dataset and conduct the first benchmark for omnidirectional visual question answering.<n>Our evaluation of state-of-the-art MLLMs reveals significant limitations in handling omnidirectional visual question answering.<n>We introduce a rule-based reinforcement learning method, 360-R1, based on Qwen2.5-VL-Instruct.
• Score: 8.039453341761538
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Omnidirectional images (ODIs), with their 360{\deg} field of view, provide unparalleled spatial awareness for immersive applications like augmented reality and embodied AI. However, the capability of existing multi-modal large language models (MLLMs) to comprehend and reason about such panoramic scenes remains underexplored. This paper addresses this gap by introducing OmniVQA, the first dataset and conducting the first benchmark for omnidirectional visual question answering. Our evaluation of state-of-the-art MLLMs reveals significant limitations in handling omnidirectional visual question answering, highlighting persistent challenges in object localization, feature extraction, and hallucination suppression within panoramic contexts. These results underscore the disconnect between current MLLM capabilities and the demands of omnidirectional visual understanding, which calls for dedicated architectural or training innovations tailored to 360{\deg} imagery. Building on the OmniVQA dataset and benchmark, we further introduce a rule-based reinforcement learning method, 360-R1, based on Qwen2.5-VL-Instruct. Concretely, we modify the group relative policy optimization (GRPO) by proposing three novel reward functions: (1) reasoning process similarity reward, (2) answer semantic accuracy reward, and (3) structured format compliance reward. Extensive experiments on our OmniVQA demonstrate the superiority of our proposed method in omnidirectional space (+6% improvement).

Related papers

• EmbRACE-3K: Embodied Reasoning and Action in Complex Environments [48.32142591866083]
  EmRACE-3K is a dataset of over 3,000 language-guided tasks constructed using Unreal Engine and the UnrealCV-Zoo framework.<n>We establish a benchmark to evaluate the embodied reasoning capabilities of VLMs across three key dimensions: Exploration, Dynamic Spatial-Semantic Reasoning, and Multi-stage Goal Execution.<n>In zero-shot settings, all models achieve success rates below 20%, underscoring the challenge posed by our benchmark and the current limitations of VLMs in interactive environments.
  arXiv  Detail & Related papers  (2025-07-14T17:59:46Z)
• SVQA-R1: Reinforcing Spatial Reasoning in MLLMs via View-Consistent Reward Optimization [57.484274282231226]
  We propose SVQA-R1, the first framework to extend R1-style training to spatial VQA.<n>In particular, we introduce Spatial-GRPO, a novel group-wise RL strategy that constructs view-consistent rewards by perturbing spatial relations between objects.<n>Our model, SVQA-R1, not only dramatically improved accuracy on spatial VQA benchmarks but also exhibits interpretable reasoning paths even without using supervised fine-tuning data.
  arXiv  Detail & Related papers  (2025-06-02T06:58:43Z)
• DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes [51.895756593200296]
  Deep Inspection and Perception with RL (DIP-R1) is designed to enhance the visual perception capabilities of MLLMs.<n>DIP-R1 guides MLLMs through detailed inspection of visual scene via three simply designed rule-based reward modelings.<n>It achieves consistent and significant improvement across various in-domain and out-of-domain scenarios.
  arXiv  Detail & Related papers  (2025-05-29T07:16:16Z)
• Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs [21.092805986558346]
  We present E3VQA, the first benchmark for multi-view question answering with 4K high-quality question-answer pairs grounded in ego-exo image pairs.<n>We also propose M3CoT, a training-free prompting technique that constructs a unified scene representation by integrating scene graphs from three complementary perspectives.
  arXiv  Detail & Related papers  (2025-05-28T04:09:42Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [47.237216851265316]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning? [66.88619941063048]
  We ask: Are multimodal large language models (MLLMs) ready for omnidirectional spatial reasoning?<n> OSR-Bench is the first benchmark specifically designed for this setting.<n>It includes over 153,000 diverse question-answer pairs grounded in high-fidelity panoramic indoor scene maps.<n>We evaluate eight state-of-the-art MLLMs, including GPT-4o, Gemini 1.5 Pro, and leading open-source models under zero-shot settings.
  arXiv  Detail & Related papers  (2025-05-17T08:48:40Z)
• Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization [18.855378039713678]
  Large Vision Language Models (VLMs) are prone to significant hallucinations, particularly in the form of cross-modal inconsistencies.<n>We introduce Re-Align, a novel alignment framework that leverages image retrieval to construct a dual-preference dataset.<n>We also introduce rDPO, an extension of the standard direct preference optimization that incorporates an additional visual preference objective during fine-tuning.
  arXiv  Detail & Related papers  (2025-02-18T18:59:57Z)
• SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models [15.50826328938879]
  We introduce SURDS, a benchmark designed to evaluate the spatial reasoning capabilities of vision language models (VLMs)<n>Built on the nuScenes dataset, SURDS comprises 41,080 vision-question-answer training instances and 9,250 evaluation samples.<n>We propose a reinforcement learning-based alignment scheme leveraging spatially grounded reward signals.
  arXiv  Detail & Related papers  (2024-11-20T08:14:01Z)
• REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models [67.55362046790512]
  Vision-language models lack the ability to correctly reason over spatial relationships. We develop the REVISION framework which improves spatial fidelity in vision-language models. Our results and findings indicate that utilizing rendering-based frameworks is an effective approach for developing spatially-aware models.
  arXiv  Detail & Related papers  (2024-08-05T04:51:46Z)
• Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement [102.22911097049953]
  Large vision-language models (LVLMs) have achieved impressive results in visual question-answering and reasoning tasks.<n>Existing methods often depend on external models or data, leading to uncontrollable and unstable alignment results.<n>We propose SIMA, a self-improvement framework that enhances visual and language modality alignment without external dependencies.
  arXiv  Detail & Related papers  (2024-05-24T23:09:27Z)
• FGAIF: Aligning Large Vision-Language Models with Fine-grained AI Feedback [16.24562885483636]
  We propose an innovative method to align modalities in Large Vision-Language Models (LVLMs) through Fine-Grained Artificial Intelligence Feedback (FGAIF)<n> Specifically, we first utilize AI tools to predict the types of hallucination for each segment in the response and obtain a collection of fine-grained feedback. Then, based on the collected reward data, three specialized reward models are trained to produce dense rewards. Finally, a novel fine-grained feedback module is integrated into the Proximal Policy Optimization (PPO) algorithm.
  arXiv  Detail & Related papers  (2024-04-07T19:00:45Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.