Learning Neural Volumetric Representations of Dynamic Humans in Minutes

• URL: http://arxiv.org/abs/2302.12237v2
• Date: Fri, 24 Feb 2023 03:13:56 GMT
• Title: Learning Neural Volumetric Representations of Dynamic Humans in Minutes
• Authors: Chen Geng, Sida Peng, Zhen Xu, Hujun Bao, Xiaowei Zhou
• Abstract summary: We propose a novel method for learning neural volumetric videos of dynamic humans from sparse view videos in minutes with competitive visual quality. Specifically, we define a novel part-based voxelized human representation to better distribute the representational power of the network to different human parts. Experiments demonstrate that our model can be learned 100 times faster than prior per-scene optimization methods.
• Score: 49.10057060558854
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper addresses the challenge of quickly reconstructing free-viewpoint videos of dynamic humans from sparse multi-view videos. Some recent works represent the dynamic human as a canonical neural radiance field (NeRF) and a motion field, which are learned from videos through differentiable rendering. But the per-scene optimization generally requires hours. Other generalizable NeRF models leverage learned prior from datasets and reduce the optimization time by only finetuning on new scenes at the cost of visual fidelity. In this paper, we propose a novel method for learning neural volumetric videos of dynamic humans from sparse view videos in minutes with competitive visual quality. Specifically, we define a novel part-based voxelized human representation to better distribute the representational power of the network to different human parts. Furthermore, we propose a novel 2D motion parameterization scheme to increase the convergence rate of deformation field learning. Experiments demonstrate that our model can be learned 100 times faster than prior per-scene optimization methods while being competitive in the rendering quality. Training our model on a $512 \times 512$ video with 100 frames typically takes about 5 minutes on a single RTX 3090 GPU. The code will be released on our project page: https://zju3dv.github.io/instant_nvr

Related papers

• D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video [53.83936023443193]
  This paper contributes to the field by introducing a new synthesis method for dynamic novel view from monocular video, such as smartphone captures. Our approach represents the as a $textitdynamic neural point cloud$, an implicit time-conditioned point cloud that encodes local geometry and appearance in separate hash-encoded neural feature grids.
  arXiv  Detail & Related papers  (2024-06-14T14:35:44Z)
• HQ3DAvatar: High Quality Controllable 3D Head Avatar [65.70885416855782]
  This paper presents a novel approach to building highly photorealistic digital head avatars. Our method learns a canonical space via an implicit function parameterized by a neural network. At test time, our method is driven by a monocular RGB video.
  arXiv  Detail & Related papers  (2023-03-25T13:56:33Z)
• Efficient Meshy Neural Fields for Animatable Human Avatars [87.68529918184494]
  Efficiently digitizing high-fidelity animatable human avatars from videos is a challenging and active research topic. Recent rendering-based neural representations open a new way for human digitization with their friendly usability and photo-varying reconstruction quality. We present EMA, a method that Efficiently learns Meshy neural fields to reconstruct animatable human Avatars.
  arXiv  Detail & Related papers  (2023-03-23T00:15:34Z)
• Mixed Neural Voxels for Fast Multi-view Video Synthesis [16.25013978657888]
  We present a novel method named MixVoxels to better represent the dynamic scenes with fast training speed and competitive rendering qualities. The proposed MixVoxels represents the 4D dynamic scenes as a mixture of static and dynamic voxels and processes them with different networks. With 15 minutes of training for dynamic scenes with inputs of 300-frame videos, MixVoxels achieves better PSNR than previous methods.
  arXiv  Detail & Related papers  (2022-12-01T00:26:45Z)
• SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video [29.50059002228373]
  SelfNeRF is an efficient neural radiance field based novel view synthesis method for human performance. It can train from scratch and achieve high-fidelity results in about twenty minutes.
  arXiv  Detail & Related papers  (2022-10-04T14:54:40Z)
• Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering [34.80975358673563]
  We propose a novel approach that learns generalizable neural radiance fields based on a parametric human body model for robust performance capture. Experiments on the ZJU-MoCap and AIST datasets show that our method significantly outperforms recent generalizable NeRF methods on unseen identities and poses.
  arXiv  Detail & Related papers  (2021-09-15T17:32:46Z)
• Fast Training of Neural Lumigraph Representations using Meta Learning [109.92233234681319]
  We develop a new neural rendering approach with the goal of quickly learning a high-quality representation which can also be rendered in real-time. Our approach, MetaNLR++, accomplishes this by using a unique combination of a neural shape representation and 2D CNN-based image feature extraction, aggregation, and re-projection. We show that MetaNLR++ achieves similar or better photorealistic novel view synthesis results in a fraction of the time that competing methods require.
  arXiv  Detail & Related papers  (2021-06-28T18:55:50Z)
• Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes [48.0304999503795]
  We introduce Stereo Radiance Fields (SRF), a neural view synthesis approach that is trained end-to-end. SRF generalizes to new scenes, and requires only sparse views at test time. Experiments show that SRF learns structure instead of overfitting on a scene.
  arXiv  Detail & Related papers  (2021-04-14T15:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.