Omniact3d improves panoramic 3d object detection using equirectangular projection
OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
Computer Vision and Pattern RecognitionArtificial IntelligenceRobotics
Summary
Detecting objects in three dimensions is important for robots and other mobile devices. The authors developed OmniAct3D, a system that helps existing 3D detectors understand full 360-degree panoramic images better. They fixed problems caused by the way panoramic images are represented and added ways to focus on important details and reasoning about object positions. Their system improved detection accuracy on multiple test sets and keeps useful knowledge from previous detectors when switching to panoramic views.
What this means in practice
- •For autonomous vehicle developers: Enable 360-degree object detection on panoramic camera inputs for safer and more accurate navigation.
- •For robotics system engineers: Incorporate OmniAct3D to improve spatial awareness of robots in complex environments with panoramic vision systems.
Authors
Runtong Wu, Fei Teng, Di Wen, Guoqiang Zhao, Kunyu Peng, Kailun Yang
Abstract
Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detectors rely on narrow-view monocular images or discrete perspective views, limiting coherent surround perception; equirectangular projection (ERP) instead encodes a continuous 360 scene in a single image. Direct transfer remains difficult because ERP organizes geometry and visual information differently, making object-relevant cues hard to model, localize, and preserve. We propose OmniAct3D, a framework that adapts perspective-trained VFM detectors to ERP while preserving transferable VFM priors. To resolve geometric mismatch, the ERP-Ray Geometry Adapter (ERGA-Ray) models spherical viewing rays and periodic spatial structure. To localize evidence in scene-wide context, the Visual-Action Reasoning Chain (VARC) grounds each hypothesis in relevant panoramic evidence and converts it into a structured geometric action. To recover local cues lost under fixed token budgets, the Appearance-Guided Heading Expert (AGHE) re-encodes object regions at higher resolution for heading estimation. Experiments show that OmniAct3D improves over the previous best 3D detector by 2.96 NDS points on Spheriverse and over the unadapted VFM baseline by 24.87 mAP points on PanoMMOcc. With target-specific geometry adaptation, VARC retains 95--98% of the same-configuration mAP, indicating reusable object-level 3D reasoning across sensing configurations. The source code will be made publicly available at https://github.com/FeiT-FeiTeng/OmniAct3D.