Computer vision for autonomous vehicles: Problems, datasets and state of the art

J Janai, F Güney, A Behl, A Geiger - Foundations and Trends® …, 2020 - nowpublishers.com
Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Barf: Bundle-adjusting neural radiance fields

CH Lin, WC Ma, A Torralba… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRF) have recently gained a surge of interest within the
computer vision community for its power to synthesize photorealistic novel views of real …

Learning depth from monocular videos using direct methods

C Wang, JM Buenaposada, R Zhu… - Proceedings of the …, 2018 - openaccess.thecvf.com
The ability to predict depth from a single image-using recent advances in CNNs-is of
increasing interest to the vision community. Unsupervised strategies to learning are …

Pixel-perfect structure-from-motion with featuremetric refinement

P Lindenberger, PE Sarlin… - Proceedings of the …, 2021 - openaccess.thecvf.com
Finding local features that are repeatable across multiple views is a cornerstone of sparse
3D reconstruction. The classical image matching paradigm detects keypoints per-image …

Bad slam: Bundle adjusted direct rgb-d slam

T Schops, T Sattler, M Pollefeys - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
A key component of Simultaneous Localization and Map** (SLAM) systems is the joint
optimization of the estimated 3D map and camera trajectory. Bundle adjustment (BA) is the …

Local-to-global registration for bundle-adjusting neural radiance fields

Y Chen, X Chen, X Wang, Q Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRF) have achieved photorealistic novel views
synthesis; however, the requirement of accurate camera poses limits its application. Despite …

Colored point cloud registration revisited

J Park, QY Zhou, V Koltun - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
We present an algorithm for tightly aligning two colored point clouds. The key idea is to
optimize a joint photometric and geometric objective that locks the alignment along both the …

Bad-nerf: Bundle adjusted deblur neural radiance fields

P Wang, L Zhao, R Ma, P Liu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRF) have received considerable attention recently, due
to its impressive capability in photo-realistic 3D reconstruction and novel view synthesis …

A survey on conventional and learning‐based methods for multi‐view stereo

EK Stathopoulou, F Remondino - The Photogrammetric Record, 2023 - Wiley Online Library
Abstract 3D reconstruction of scenes using multiple images, relying on robust
correspondence search and depth estimation, has been thoroughly studied for the two‐view …

Ba-net: Dense bundle adjustment network

C Tang, P Tan - arxiv preprint arxiv:1806.04807, 2018 - arxiv.org
This paper introduces a network architecture to solve the structure-from-motion (SfM)
problem via feature-metric bundle adjustment (BA), which explicitly enforces multi-view …