DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

• URL: http://arxiv.org/abs/2205.01666v1
• Date: Tue, 3 May 2022 17:56:46 GMT
• Title: DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks
• Authors: Shih-Yang Su, Timur Bagautdinov, Helge Rhodin
• Abstract summary: High-resolution models enable photo-realistic avatars but at the cost of requiring studio settings not available to end users. Our goal is to create avatars directly from raw images without relying on expensive studio setups and surface tracking. We introduce a three-stage method that induces two inductive biases to better disentangled pose-dependent deformation.
• Score: 12.132886846993108
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning greatly improved the realism of animatable human models by learning geometry and appearance from collections of 3D scans, template meshes, and multi-view imagery. High-resolution models enable photo-realistic avatars but at the cost of requiring studio settings not available to end users. Our goal is to create avatars directly from raw images without relying on expensive studio setups and surface tracking. While a few such approaches exist, those have limited generalization capabilities and are prone to learning spurious (chance) correlations between irrelevant body parts, resulting in implausible deformations and missing body parts on unseen poses. We introduce a three-stage method that induces two inductive biases to better disentangled pose-dependent deformation. First, we model correlations of body parts explicitly with a graph neural network. Second, to further reduce the effect of chance correlations, we introduce localized per-bone features that use a factorized volumetric representation and a new aggregation function. We demonstrate that our model produces realistic body shapes under challenging unseen poses and shows high-quality image synthesis. Our proposed representation strikes a better trade-off between model capacity, expressiveness, and robustness than competing methods. Project website: https://lemonatsu.github.io/danbo.

Related papers

• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• 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)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose [42.4185273307021]
  We present imGHUM, the first holistic generative model of 3D human shape and articulated pose. We model the full human body implicitly as a function zero-level-set and without the use of an explicit template mesh.
  arXiv  Detail & Related papers  (2021-08-24T17:08:28Z)
• Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing [49.32522765356914]
  We learn to animate people in clothing as a function of the body pose. We learn to map every point in the space to a canonical space, where a learned deformation field is applied to model non-rigid effects. Neural-GIF can be trained on raw 3D scans and reconstructs detailed complex surface geometry and deformations.
  arXiv  Detail & Related papers  (2021-08-19T17:25:16Z)
• 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)
• SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks [54.94737477860082]
  We present an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar. SCANimate does not rely on a customized mesh template or surface mesh registration. Our method can be applied to pose-aware appearance modeling to generate a fully textured avatar.
  arXiv  Detail & Related papers  (2021-04-07T17:59:58Z)

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.