DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

by   Jia-Wei Liu, et al.

Modeling dynamic scenes is important for many applications such as virtual reality and telepresence. Despite achieving unprecedented fidelity for novel view synthesis in dynamic scenes, existing methods based on Neural Radiance Fields (NeRF) suffer from slow convergence (i.e., model training time measured in days). In this paper, we present DeVRF, a novel representation to accelerate learning dynamic radiance fields. The core of DeVRF is to model both the 3D canonical space and 4D deformation field of a dynamic, non-rigid scene with explicit and discrete voxel-based representations. However, it is quite challenging to train such a representation which has a large number of model parameters, often resulting in overfitting issues. To overcome this challenge, we devise a novel static-to-dynamic learning paradigm together with a new data capture setup that is convenient to deploy in practice. This paradigm unlocks efficient learning of deformable radiance fields via utilizing the 3D volumetric canonical space learnt from multi-view static images to ease the learning of 4D voxel deformation field with only few-view dynamic sequences. To further improve the efficiency of our DeVRF and its synthesized novel view's quality, we conduct thorough explorations and identify a set of strategies. We evaluate DeVRF on both synthetic and real-world dynamic scenes with different types of deformation. Experiments demonstrate that DeVRF achieves two orders of magnitude speedup (100x faster) with on-par high-fidelity results compared to the previous state-of-the-art approaches. The code and dataset will be released in


page 3

page 5

page 6

page 7

page 9

page 10

page 11

page 13


Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis

Recently, Neural Radiance Fields (NeRF) is revolutionizing the task of n...

Mixed Neural Voxels for Fast Multi-view Video Synthesis

Synthesizing high-fidelity videos from real-world multi-view input is ch...

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields

Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprec...

Fast Dynamic Radiance Fields with Time-Aware Neural Voxels

Neural radiance fields (NeRF) have shown great success in modeling 3D sc...

DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies

We introduce a supervised-learning framework for non-rigid point set ali...

Deformable Neural Radiance Fields

We present the first method capable of photorealistically reconstructing...

Fast-SNARF: A Fast Deformer for Articulated Neural Fields

Neural fields have revolutionized the area of 3D reconstruction and nove...

Please sign up or login with your details

Forgot password? Click here to reset