CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentations

• URL: http://arxiv.org/abs/2605.19649v2
• Date: Wed, 20 May 2026 14:07:34 GMT
• Title: CAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based Augmentations
• Abstract summary: Spacecraft pose estimation networks require tens of thousands of CAD-rendered images to be trained.<n>NeRF-based image augmentation method generates a large, diverse dataset through geometrically-consistent viewpoint and appearance augmentation.<n>Experiments show that our approach supports the training of accurate pose estimators from only 25 to 400 realistic images, even under severe illumination variations.
• Score: 14.365830773250929
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spacecraft pose estimation networks require tens of thousands of CAD-rendered images to be trained. This reliance on synthetic CAD data (i) limits applicability to targets with reliable geometry prior, excluding uncooperative or poorly documented spacecraft, and (ii) causes poor generalization to real on-orbit conditions due to unrealistic illumination and material appearance. This paper introduces a NeRF-based image augmentation method that enables the learning of spacecraft pose estimators from only a few tens to a few hundreds of images. The method learns a Neural Radiance Field of the target and generates a large, diverse dataset through geometrically-consistent viewpoint and appearance augmentation. This augmented dataset enables the training of accurate target-specific pose estimators without requiring a CAD model or large synthetic datasets. Experiments show that our approach supports the training of accurate pose estimators from only 25 to 400 realistic images, even under severe illumination variations. When applied on large CAD-based synthetic datasets, the NeRF-based augmentation also enhances out-of-domain generalization, yielding improved robustness to real on-orbit conditions.

Related papers

• AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World [75.54693105865003]
  We introduce AerialMetric, a benchmark dataset to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints.<n>AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth.
  arXiv  Detail & Related papers  (2026-06-29T02:48:47Z)
• From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation [0.0]
  We present a novel approach utilizing spatial conditioning techniques within a foundation model to transform satellite SAR imagery into airborne SAR representations.<n>Our method explores a key application of AI in advancing SAR imaging technology.
  arXiv  Detail & Related papers  (2025-05-05T09:33:06Z)
• CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images [69.7768227804928]
  CADCrafter is an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data.<n>We introduce a geometry encoder to accurately capture diverse geometric features.<n>Our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.
  arXiv  Detail & Related papers  (2025-04-07T06:01:35Z)
• SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery [8.096413986108601]
  We introduce SatVision-TOA, a novel foundation model pre-trained on 14-band MODIS L1B Top-Of-Atmosphere (TOA) radiance imagery. The SatVision-TOA model is pre-trained using a Masked-Image-Modeling (MIM) framework and the SwinV2 architecture. Results show that SatVision-TOA achieves superior performance over baseline methods on downstream tasks.
  arXiv  Detail & Related papers  (2024-11-26T00:08:00Z)
• Towards Degradation-Robust Reconstruction in Generalizable NeRF [58.33351079982745]
  Generalizable Radiance Field (GNeRF) across scenes has been proven to be an effective way to avoid per-scene optimization. There has been limited research on the robustness of GNeRFs to different types of degradation present in the source images.
  arXiv  Detail & Related papers  (2024-11-18T16:13:47Z)
• Analysis of Classifier Training on Synthetic Data for Cross-Domain Datasets [4.696575161583618]
  This study focuses on camera-based traffic sign recognition applications for advanced driver assistance systems and autonomous driving. The proposed augmentation pipeline of synthetic datasets includes novel augmentation processes such as structured shadows and gaussian specular highlights. Experiments showed that a synthetic image-based approach outperforms in most cases real image-based training when applied to cross-domain test datasets.
  arXiv  Detail & Related papers  (2024-10-30T07:11:41Z)
• Leveraging Neural Radiance Fields for Pose Estimation of an Unknown Space Object during Proximity Operations [14.624172952608653]
  We present a novel method that enables an "off-the-shelf" spacecraft pose estimator to be applied on an unknown target. We train the NeRF model using a sparse collection of images that depict the target, and in turn generate a large dataset that is diverse both in terms of viewpoint and illumination. We demonstrate that our method successfully enables the training of an off-the-shelf spacecraft pose estimation network from a sparse set of images.
  arXiv  Detail & Related papers  (2024-05-21T12:34:03Z)
• Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs [59.12526668734703]
  We introduce Composable Object Volume NeRF (COV-NeRF), an object-composable NeRF model that is the centerpiece of a real-to-sim pipeline. COV-NeRF extracts objects from real images and composes them into new scenes, generating photorealistic renderings and many types of 2D and 3D supervision.
  arXiv  Detail & Related papers  (2024-03-07T00:00:02Z)
• Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets [5.391764618878545]
  In this paper, we aim to scale the Neural Radiance Fields (NeRF) on large-scael aerial datasets. Specifically, we introduce a location-specific sampling technique as well as a multi-camera tiling (MCT) strategy to reduce memory consumption. We implement our method on a representative approach, Mip-NeRF, and compare its geometry performance with threephotgrammetric MVS pipelines.
  arXiv  Detail & Related papers  (2023-10-01T00:21:01Z)
• Pose-Free Neural Radiance Fields via Implicit Pose Regularization [117.648238941948]
  IR-NeRF is an innovative pose-free neural radiance field (NeRF) that introduces implicit pose regularization to refine pose estimator with unposed real images. With a collection of 2D images of a specific scene, IR-NeRF constructs a scene codebook that stores scene features and captures the scene-specific pose distribution implicitly as priors.
  arXiv  Detail & Related papers  (2023-08-29T06:14:06Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)

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.