Benchmarking neural radiance fields for autonomous robots: An overview

Y Ming, X Yang, W Wang, Z Chen, J Feng… - … Applications of Artificial …, 2025‏ - Elsevier
Abstract Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene
representation, offering high-fidelity renderings and reconstructions from a set of sparse and …

Scene coordinate reconstruction: Posing of image collections via incremental learning of a relocalizer

E Brachmann, J Wynn, S Chen, T Cavallari… - … on Computer Vision, 2024‏ - Springer
We address the task of estimating camera parameters from a set of images depicting a
scene. Popular feature-based structure-from-motion (SfM) tools solve this task by …

Pope: 6-dof promptable pose estimation of any object in any scene with one reference

Z Fan, P Pan, P Wang, Y Jiang… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation
existing methods have limited applicability in real-world scenarios involving embodied …

Crossfire: Camera relocalization on self-supervised features from an implicit representation

A Moreau, N Piasco, M Bennehar… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Beyond novel view synthesis, Neural Radiance Fields are useful for applications that
interact with the real world. In this paper, we use them as an implicit map of a given scene …

Scanerf: Scalable bundle-adjusting neural radiance fields for large-scale scene rendering

X Wu, J Xu, X Zhang, H Bao, Q Huang, Y Shen… - ACM Transactions on …, 2023‏ - dl.acm.org
High-quality large-scale scene rendering requires a scalable representation and accurate
camera poses. This research combines tile-based hybrid neural fields with parallel …

Ai-generated images as data source: The dawn of synthetic era

Z Yang, F Zhan, K Liu, M Xu, S Lu - arxiv preprint arxiv:2310.01830, 2023‏ - arxiv.org
The advancement of visual intelligence is intrinsically tethered to the availability of large-
scale data. In parallel, generative Artificial Intelligence (AI) has unlocked the potential to …

Learning to estimate 6dof pose from limited data: A few-shot, generalizable approach using rgb images

P Pan, Z Fan, BY Feng, P Wang, C Li… - … Conference on 3D …, 2024‏ - ieeexplore.ieee.org
The accurate estimation of six degrees-of-freedom (6DoF) object poses is essential for many
applications in robotics and augmented reality. However, existing methods for 6DoF pose …

6dgs: 6d pose estimation from a single image and a 3d gaussian splatting model

B Matteo, T Tsesmelis, S James, F Poiesi… - European Conference on …, 2024‏ - Springer
We propose 6DGS to estimate the camera pose of a target RGB image given a 3D Gaussian
Splatting (3DGS) model representing the scene. 6DGS avoids the iterative process typical of …

Nerf in robotics: A survey

G Wang, L Pan, S Peng, S Liu, C Xu, Y Miao… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Meticulous 3D environment representations have been a longstanding goal in computer
vision and robotics fields. The recent emergence of neural implicit representations has …

Nvist: In the wild new view synthesis from a single image with transformers

W Jang, L Agapito - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
We propose NViST a transformer-based model for efficient and generalizable novel-view
synthesis from a single image for real-world scenes. In contrast to many methods that are …