paper-with-me

Papers

Compressing Explicit Voxel Grid Representations: fast NeRFs become also small

2022-10-23 · Chenxi Lola Deng, Enzo Tartaglione

NeRFs have revolutionized the world of per-scene radiance field reconstruction because of their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering speed, both at training and inference time. Recent research focuses on the optimization of an explicit voxel grid (EVG) that represents the scene, which can be paired with neural networks to learn radiance fields. This approach significantly enhances the speed both at train and inference time, but at the cost of large memory occupation. In this work we propose Re:NeRF, an approach that specifically targets EVG-NeRFs compressibility, aiming to reduce memory storage of NeRF models while maintaining comparable performance. We benchmark our approach with three different EVG-NeRF architectures on four popular benchmarks, showing Re:NeRF's broad usability and effectiveness.

📄 PDF Abstract BibTeX arXiv:2210.12782

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

2021-11-22 · CVPR 2022 1 · Cheng Sun, Min Sun, Hwann-Tzong Chen

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is rece…

GPUNeRFNovel View Synthesis

Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views

2024-03-04 · Shuai Guo, Qiuwen Wang, Yijie Gao, Rong Xie 외

Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging …

Autonomous DrivingNeRFNovel View Synthesis

Deep Implicit Volume Compression

2020-05-18 · CVPR 2020 6 · Danhang Tang, Saurabh Singh, Philip A. Chou, Christian Haene 외

We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network arc…

Video Compression

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

Multi-level 3D CNN for Learning Multi-scale Spatial Features

2018-05-30 · Sambit Ghadai, Xian Lee, Aditya Balu, Soumik Sarkar 외

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep lea…

3D Object RecognitionObjectObject Recognition