{
  "id": "2403.15705",
  "version": "v1",
  "published": "2024-03-23T03:56:25.000Z",
  "updated": "2024-03-23T03:56:25.000Z",
  "title": "UPNeRF: A Unified Framework for Monocular 3D Object Reconstruction and Pose Estimation",
  "authors": [
    "Yuliang Guo",
    "Abhinav Kumar",
    "Cheng Zhao",
    "Ruoyu Wang",
    "Xinyu Huang",
    "Liu Ren"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose. While gradient-based optimization within a NeRF framework updates initially given poses, this paper highlights that such a scheme fails when the initial pose even moderately deviates from the true pose. Consequently, existing methods often depend on a third-party 3D object to provide an initial object pose, leading to increased complexity and generalization issues. To address these challenges, we present UPNeRF, a Unified framework integrating Pose estimation and NeRF-based reconstruction, bringing us closer to real-time monocular 3D object reconstruction. UPNeRF decouples the object's dimension estimation and pose refinement to resolve the scale-depth ambiguity, and introduces an effective projected-box representation that generalizes well cross different domains. While using a dedicated pose estimator that smoothly integrates into an object-centric NeRF, UPNeRF is free from external 3D detectors. UPNeRF achieves state-of-the-art results in both reconstruction and pose estimation tasks on the nuScenes dataset. Furthermore, UPNeRF exhibits exceptional Cross-dataset generalization on the KITTI and Waymo datasets, surpassing prior methods with up to 50% reduction in rotation and translation error.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-03-23T03:56:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "unified framework",
      "framework integrating pose estimation",
      "real-time monocular 3d object reconstruction",
      "upnerf achieves state-of-the-art results",
      "external 3d detectors"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}