paper-with-me

홈 › Papers

PlenVDB: Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering

2023-01-01 · CVPR 2023 1 · Han Yan, Celong Liu, Chao Ma, Xing Mei

In this paper, we present a new representation for neural radiance fields that accelerates both the training and the inference processes with VDB, a hierarchical data structure for sparse volumes. VDB takes both the advantages of sparse and dense volumes for compact data representation and efficient data access, being a promising data structure for NeRF data interpolation and ray marching. Our method, Plenoptic VDB (PlenVDB), directly learns the VDB data structure from a set of posed images by means of a novel training strategy and then uses it for real-time rendering. Experimental results demonstrate the effectiveness and the efficiency of our method over previous arts: First, it converges faster in the training process. Second, it delivers a more compact data format for NeRF data presentation. Finally, it renders more efficiently on commodity graphics hardware. Our mobile PlenVDB demo achieves 30+ FPS, 1280x720 resolution on an iPhone12 mobile phone. Check plenvdb.github.io for details.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

Similar Papers 제목 키워드 기반

MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

2023-02-23 · Christian Reiser, Richard Szeliski, Dor Verbin, Pratul P. Srinivasan 외

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale …

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices

2026-04-03 · Kim Jun-Seong, Mingyu Kim, GeonU Kim, Tae-Hyun Oh 외 arxiv

We introduce Fact-Hash, a novel parameter-encoding method for training on-device neural radiance fields. Neural Radiance Fields (NeRF) have proven pivotal in 3D representations, but their applications are limited due to …

Computational Efficiency

Compressing Volumetric Radiance Fields to 1 MB

2022-11-29 · CVPR 2023 1 · Lingzhi Li, Zhen Shen, Zhongshu Wang, Li Shen 외

Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering…

Model CompressionNeRFNeural RenderingQuantization

Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields

2023-11-21 · Yifan Wang, Yi Gong, Yuan Zeng

Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume renderin…

NeRFNovel View Synthesis

Fast Learning Radiance Fields by Shooting Much Fewer Rays

2022-08-14 · Wenyuan Zhang, Ruofan Xing, Yunfan Zeng, Yu-Shen Liu 외

Learning radiance fields has shown remarkable results for novel view synthesis. The learning procedure usually costs lots of time, which motivates the latest methods to speed up the learning procedure by learning without…

Novel View Synthesis