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 …

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

A Engelhardt, A Raj, M Boss, Y Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
We present SHINOBI an end-to-end framework for the reconstruction of shape material and
illumination from object images captured with varying lighting pose and background. Inverse …

3D Congealing: 3D-Aware Image Alignment in the Wild

Y Zhang, Z Li, A Raj, A Engelhardt, Y Li, T Hou… - … on Computer Vision, 2024 - Springer
We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images
capturing semantically similar objects. Given a collection of unlabeled Internet images, our …

Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis

Q Zhao, S Tulsiani - arxiv preprint arxiv:2412.03570, 2024 - arxiv.org
Inferring the 3D structure underlying a set of multi-view images typically requires solving two
co-dependent tasks--accurate 3D reconstruction requires precise camera poses, and …

Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching

Y Sun, C Sun, Y Liu, Y Ma, SM Yiu - arxiv preprint arxiv:2411.15860, 2024 - arxiv.org
In this paper, we present a novel generalizable object pose estimation method to determine
the object pose using only one RGB image. Unlike traditional approaches that rely on …

Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Views

S Zhang, C Zhao - arxiv preprint arxiv:2412.08412, 2024 - arxiv.org
Inferring 3D structures from sparse, unposed observations is challenging due to its
unconstrained nature. Recent methods propose to predict implicit representations directly …

[BUCH][B] Computer Vision-ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXIV.

A Leonardis - 2024 - books.google.com
The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes
the refereed proceedings of the 18th European Conference on Computer Vision, ECCV …