paper-with-me

홈 › Papers

Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis

2022-06-15 · Xiang Guo, GuanYing Chen, Yuchao Dai, Xiaoqing Ye, Jiadai Sun, Xiao Tan, Errui Ding

Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of novel view synthesis (NVS) for its superior performance. In this paper, we propose to synthesize dynamic scenes. Extending the methods for static scenes to dynamic scenes is not straightforward as both the scene geometry and appearance change over time, especially under monocular setup. Also, the existing dynamic NeRF methods generally require a lengthy per-scene training procedure, where multi-layer perceptrons (MLP) are fitted to model both motions and radiance. In this paper, built on top of the recent advances in voxel-grid optimization, we propose a fast deformable radiance field method to handle dynamic scenes. Our method consists of two modules. The first module adopts a deformation grid to store 3D dynamic features, and a light-weight MLP for decoding the deformation that maps a 3D point in the observation space to the canonical space using the interpolated features. The second module contains a density and a color grid to model the geometry and density of the scene. The occlusion is explicitly modeled to further improve the rendering quality. Experimental results show that our method achieves comparable performance to D-NeRF using only 20 minutes for training, which is more than 70x faster than D-NeRF, clearly demonstrating the efficiency of our proposed method.

📄 PDF Abstract BibTeX arXiv:2206.07698

Code (0)

등록된 구현이 없습니다.

Tasks

NeRFNovel View Synthesis

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

Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction

2023-04-12 · Xiangyu Xu, Lichang Chen, Changjiang Cai, Huangying Zhan 외

Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules. However, this approach is constrained by higher memory expenses and limited re…

Computational EfficiencySurface Reconstruction

Deformable Voxel Grids for Shape Comparisons

2022-11-21 · Raphaël Groscot, Laurent D. Cohen

We present Deformable Voxel Grids (DVGs) for 3D shapes comparison and processing. It consists of a voxel grid which is deformed to approximate the silhouette of a shape, via energy-minimization. By interpreting the DVG a…

RetrievalStyle Transfer

VGOS: Voxel Grid Optimization for View Synthesis from Sparse Inputs

2023-04-26 · Jiakai Sun, Zhanjie Zhang, Jiafu Chen, Guangyuan Li 외

Neural Radiance Fields (NeRF) has shown great success in novel view synthesis due to its state-of-the-art quality and flexibility. However, NeRF requires dense input views (tens to hundreds) and a long training time (hou…

NeRFNovel View Synthesis

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

TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization

2024-02-22 · Renyi Mao, Qingshan Xu, Peng Zheng, Ye Wang 외

Coordinate-based neural implicit representation or implicit fields have been widely studied for 3D geometry representation or novel view synthesis. Recently, a series of efforts have been devoted to accelerating the spee…

3D geometryNeRFNovel View Synthesis