Droid-slam: Deep visual slam for monocular, stereo, and rgb-d cameras

Z Teed, J Deng - Advances in neural information …, 2021 - proceedings.neurips.cc
We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM
consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense …

Visual SLAM integration with semantic segmentation and deep learning: A review

H Pu, J Luo, G Wang, T Huang, H Liu - IEEE Sensors Journal, 2023 - ieeexplore.ieee.org
Simultaneous localization and map** (SLAM) technology is essential for robots to
navigate unfamiliar environments. It utilizes the sensors the robot carries to answer the …

Toward general-purpose robots via foundation models: A survey and meta-analysis

Y Hu, Q **e, V Jain, J Francis, J Patrikar… - arxiv preprint arxiv …, 2023 - arxiv.org
Building general-purpose robots that operate seamlessly in any environment, with any
object, and utilizing various skills to complete diverse tasks has been a long-standing goal in …

Infinite photorealistic worlds using procedural generation

A Raistrick, L Lipson, Z Ma, L Mei… - Proceedings of the …, 2023 - openaccess.thecvf.com
We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural
world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from …

Deep patch visual odometry

Z Teed, L Lipson, J Deng - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Abstract We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for
monocular Visual Odometry (VO). DPVO uses a novel recurrent network architecture …

Relpose: Predicting probabilistic relative rotation for single objects in the wild

JY Zhang, D Ramanan, S Tulsiani - European Conference on Computer …, 2022 - Springer
We describe a data-driven method for inferring the camera viewpoints given multiple images
of an arbitrary object. This task is a core component of classic geometric pipelines such as …

Deep patch visual slam

L Lipson, Z Teed, J Deng - European Conference on Computer Vision, 2024 - Springer
Abstract Recent work in Visual Odometry and SLAM has shown the effectiveness of using
deep network backbones. Despite excellent accuracy, such approaches are often expensive …

Autonomous drone racing: A survey

D Hanover, A Loquercio, L Bauersfeld… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Over the last decade, the use of autonomous drone systems for surveying, search and
rescue, or last-mile delivery has increased exponentially. With the rise of these applications …

Monst3r: A simple approach for estimating geometry in the presence of motion

J Zhang, C Herrmann, J Hur, V Jampani… - arxiv preprint arxiv …, 2024 - arxiv.org
Estimating geometry from dynamic scenes, where objects move and deform over time,
remains a core challenge in computer vision. Current approaches often rely on multi-stage …

XVO: Generalized visual odometry via cross-modal self-training

L Lai, Z Shangguan, J Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose XVO, a semi-supervised learning method for training generalized monocular
Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and …