Vision-Only Robot Navigation in a Neural Radiance World

Adamkiewicz, Michal; Chen, Timothy; Caccavale, Adam; Gardner, Rachel; Culbertson, Preston; Bohg, Jeannette; Schwager, Mac

doi:10.48550/arxiv.2110.00168

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other notable works tackle SDF reconstruction in dynamic environments with composite fields [13] and in very large environments using submaps [27]. Lastly, other related directions tackle learning cost fields for motion planning [6,9,33] from SDFs [11,16], navigating in a neural radiance fields [1] and learning neural fields for articulated [18] or deformable objects [35] for manipulation.…”

Section: Related Workmentioning

confidence: 99%

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

Ortiz¹,

Clegg²,

Dong³

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

Ortiz¹,

Clegg²,

Dong³

et al. 2022

Preprint

View full text Add to dashboard Cite

“…These works have potential to make substantial impacts not only in computer vision and computer graphics, but also in robotics [1,30], virtual reality (VR) systems [4,23,42,72], and medical imaging [71]. Despite NeRF's high quality 3D renderings, a key bottleneck has been slow training and inference speeds where the original implementation took days to render an object and tens of seconds to render a view angle [41].…”

Section: Introductionmentioning

confidence: 99%

VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field

Kondo¹,

Ikeda²,

Tagliasacchi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural Radiance Field (NeRF) is a popular method in data-driven 3D reconstruction. Given its simplicity and high quality rendering, many NeRF applications are being developed. However, NeRF's big limitation is its slow speed. Many attempts are made to speeding up NeRF training and inference, including intricate code-level optimization and caching, use of sophisticated data structures, and amortization through multi-task and meta learning. In this work, we revisit the basic building blocks of NeRF through the lens of classic techniques before NeRF. We propose Voxel-Accelearated NeRF (VaxNeRF), integrating NeRF with visual hull, a classic 3D reconstruction technique only requiring binary foreground-background pixel labels per image. Visual hull, which can be optimized in about 10 seconds, can provide coarse in-out field separation to omit substantial amounts of network evaluations in NeRF. We provide a clean fully-pythonic, JAX-based implementation on the popular JaxNeRF codebase, consisting of only about 30 lines of code changes and a modular visual hull subroutine, and achieve about 2-8x faster learning on top of the highly-performative JaxNeRF baseline with zero degradation in rendering quality. With sufficient compute, this effectively brings down full NeRF training from hours to 30 minutes. We hope VaxNeRF -a careful combination of a classic technique with a deep method (that arguably replaced it) -can empower and accelerate new NeRF extensions and applications, with its simplicity, portability, and reliable performance gains. Codes are available at https://github.com/naruya/VaxNeRF. (a) NeRF (b) VaxNeRF Figure 1. NeRF (a) uses hierarchical sampling, i.e., a mixture of coarse (pink) and fine (light blue) sampling, to estimate the color from a specified viewpoint. Instead, VaxNeRF (b) samples only the inside of the bounding volume uniformly and densely. The orange circle shows the area bounded by the minimum and maximum distances of the rays, and the black shade in (b) shows the automatically obtained bounding volume.

show abstract

Vision-Only Robot Navigation in a Neural Radiance World

Cited by 2 publications

References 0 publications

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field

Contact Info

Product

Resources

About