Neural Rendering of Humans in Novel View and Pose from Monocular Video

• URL: http://arxiv.org/abs/2204.01218v2
• Date: Thu, 20 Apr 2023 04:08:04 GMT
• Title: Neural Rendering of Humans in Novel View and Pose from Monocular Video
• Authors: Tiantian Wang, Nikolaos Sarafianos, Ming-Hsuan Yang, Tony Tung
• Abstract summary: We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.
• Score: 68.37767099240236
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Despite the significant progress recently on this topic, with several methods exploring shared canonical neural radiance fields in dynamic scene scenarios, learning a user-controlled model for unseen poses remains a challenging task. To tackle this problem, we introduce an effective method to a) integrate observations across several frames and b) encode the appearance at each individual frame. We accomplish this by utilizing both the human pose that models the body shape as well as point clouds that partially cover the human as input. Our approach simultaneously learns a shared set of latent codes anchored to the human pose among several frames, and an appearance-dependent code anchored to incomplete point clouds generated by each frame and its predicted depth. The former human pose-based code models the shape of the performer whereas the latter point cloud-based code predicts fine-level details and reasons about missing structures at the unseen poses. To further recover non-visible regions in query frames, we employ a temporal transformer to integrate features of points in query frames and tracked body points from automatically-selected key frames. Experiments on various sequences of dynamic humans from different datasets including ZJU-MoCap show that our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.

Related papers

• MonoHuman: Animatable Human Neural Field from Monocular Video [30.113937856494726]
  We propose a novel framework MonoHuman, which robustly renders view-consistent and high-fidelity avatars under arbitrary novel poses. Our key insight is to model the deformation field with bi-directional constraints and explicitly leverage the off-the-peg information to reason the feature for coherent results.
  arXiv  Detail & Related papers  (2023-04-04T17:55:03Z)
• Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors [98.24047528960406]
  We propose a new method for learning a generalized animatable neural representation from a sparse set of multi-view imagery of multiple persons. The learned representation can be used to synthesize novel view images of an arbitrary person from a sparse set of cameras, and further animate them with the user's pose control.
  arXiv  Detail & Related papers  (2022-08-25T07:36:46Z)
• Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis [52.720314035084215]
  This work targets at using a general deep learning framework to synthesize free-viewpoint images of arbitrary human performers. We present a simple yet powerful framework, named Generalizable Neural Performer (GNR), that learns a generalizable and robust neural body representation. Experiments on GeneBody-1.0 and ZJU-Mocap show better robustness of our methods than recent state-of-the-art generalizable methods.
  arXiv  Detail & Related papers  (2022-04-25T17:14:22Z)
• 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)
• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images [60.56518548286836]
  To generate realistic cloth deformations from novel input poses, watertight meshes or dense full-body scans are usually needed as inputs. We propose an approach that can quickly generate realistic clothed human avatars, represented as controllable neural SDFs, given only monocular depth images.
  arXiv  Detail & Related papers  (2021-06-22T17:30:12Z)
• Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control [80.79820002330457]
  We propose a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method achieves better quality than the state-of-the-arts on playback as well as novel pose synthesis, and can even generalize well to new poses that starkly differ from the training poses.
  arXiv  Detail & Related papers  (2021-06-03T17:40:48Z)
• Deep Dual Consecutive Network for Human Pose Estimation [44.41818683253614]
  We propose a novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection. Our method ranks No.1 in the Multi-frame Person Pose Challenge Challenge on the large-scale benchmark datasets PoseTrack 2017 and PoseTrack 2018.
  arXiv  Detail & Related papers  (2021-03-12T13:11:27Z)
• Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans [56.63912568777483]
  This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. We propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh. Experiments on ZJU-MoCap show that our approach outperforms prior works by a large margin in terms of novel view synthesis quality.
  arXiv  Detail & Related papers  (2020-12-31T18:55:38Z)

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.