DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering

Wu, Liwen; Lee, Jae Yong; Bhattad, Anand; Wang, Yu-Xiong; Forsyth, David

doi:10.1109/cvpr52688.2022.01572

Cited by 49 publications

(33 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, there has also been a flood of new approaches [PC21, FXW*21,YFKT*21, WLB*21,SSC21, KIT*21] that employ classical data structures, such as grids, sparse grids, trees, and hashes, for acceleration of rendering speed as well as faster training times. Instant Neural Graphics Primitives [MESK22] enables the training of a NeRF in a few seconds exploiting a multi‐resolution hash encoding instead of an explicit grid structure.…”

Section: Applicationsmentioning

confidence: 99%

Advances in Neural Rendering

Tewari

Thies²,

Mildenhall

et al. 2022

Computer Graphics Forum

152

View full text Add to dashboard Cite

show abstract

Section: Applicationsmentioning

confidence: 99%

Advances in Neural Rendering

Tewari

Thies²,

Mildenhall

et al. 2022

Computer Graphics Forum

152

View full text Add to dashboard Cite

show abstract

“…To improve the speed, it is feasible to change the MLP, which is the most time consuming part. For example, introducing a voxel grid with a small network for implicit storage and rendering [32], [33], or taking neural 3D point cloud [34], or even abandon the network structure directly [35]. Reducing the number of sampling points can also improve rendering speed [9], [36].…”

Section: B Nerf Series Methodsmentioning

confidence: 99%

DR-WLC: Dimensionality Reduction cognition for object detection and pose estimation by Watching, Learning and Checking

Gao¹,

Xu²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Object detection and pose estimation are difficult tasks in robotics and autonomous driving. Existing object detection and pose estimation methods mostly adopt the samedimensional data for training. For example, 2D object detection usually requires a large amount of 2D annotation data with high cost. Using high-dimensional information to supervise lower-dimensional tasks is a feasible way to reduce datasets size. In this work, the DR-WLC, a dimensionality reduction cognitive model, which can perform both object detection and pose estimation tasks at the same time is proposed. The model only requires 3D model of objects and unlabeled environment images (with or without objects) to finish the training. In addition, a bounding boxes generation strategy is also proposed to build the relationship between 3D model and 2D object detection task. Experiments show that our method can qualify the work without any manual annotations and it is easy to deploy for practical applications. Source code is at https: //github.com/IN2-ViAUn/DR-WLC.

show abstract

“…Alternatively, faster rendering can be achieved by extending the network to work with ray segments rather than points [Lindell et al 2021;Wu et al 2022a] or by training a separate sampling network Kurz et al 2022;Neff et al 2021;Piala and Clark 2021]. However, these approaches have not achieved real-time rates at high resolutions, likely because they require evaluating an MLP for each sample along a ray.…”

Section: Related Workmentioning

confidence: 99%