LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space

• URL: http://arxiv.org/abs/2203.07881v1
• Date: Tue, 15 Mar 2022 13:22:57 GMT
• Title: LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space
• Authors: Emre Aksan, Shugao Ma, Akin Caliskan, Stanislav Pidhorskyi, Alexander Richard, Shih-En Wei, Jason Saragih, Otmar Hilliges
• Abstract summary: We introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. A normalizing flow bridges the two representation spaces and transforms latent samples from one domain to another, allowing us to define a latent likelihood objective. We show that our approach leads to an expressive and effective prior, capturing facial dynamics and subtle expressions better.
• Score: 90.74976459491303
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by headset-mounted cameras or a front-facing camera, and sparse facial landmarks. To mitigate this asymmetry, we introduce a prior model that is conditioned on the runtime inputs and tie this prior space to the 3D face model via a normalizing flow in the latent space. Our proposed model, LiP-Flow, consists of two encoders that learn representations from the rich training-time and impoverished inference-time observations. A normalizing flow bridges the two representation spaces and transforms latent samples from one domain to another, allowing us to define a latent likelihood objective. We trained our model end-to-end to maximize the similarity of both representation spaces and the reconstruction quality, making the 3D face model aware of the limited driving signals. We conduct extensive evaluations where the latent codes are optimized to reconstruct 3D avatars from partial or sparse observations. We show that our approach leads to an expressive and effective prior, capturing facial dynamics and subtle expressions better.

Related papers

• DiHuR: Diffusion-Guided Generalizable Human Reconstruction [51.31232435994026]
  We introduce DiHuR, a Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision.
  arXiv  Detail & Related papers  (2024-11-16T03:52:23Z)
• SPARK: Self-supervised Personalized Real-time Monocular Face Capture [6.093606972415841]
  Current state of the art approaches have the ability to regress parametric 3D face models in real-time across a wide range of identities. We propose a method for high-precision 3D face capture taking advantage of a collection of unconstrained videos of a subject as prior information.
  arXiv  Detail & Related papers  (2024-09-12T12:30:04Z)
• Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models [3.9373541926236766]
  We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. We show that our approach enables generating 3D scenes in as little as 0.2 seconds, either from scratch, or from sparse input views.
  arXiv  Detail & Related papers  (2024-06-18T23:14:29Z)
• DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features [65.8738034806085]
  DistillNeRF is a self-supervised learning framework for understanding 3D environments in autonomous driving scenes. Our method is a generalizable feedforward model that predicts a rich neural scene representation from sparse, single-frame multi-view camera inputs.
  arXiv  Detail & Related papers  (2024-06-17T21:15:13Z)
• Personalized 3D Human Pose and Shape Refinement [19.082329060985455]
  regression-based methods have dominated the field of 3D human pose and shape estimation. We propose to construct dense correspondences between initial human model estimates and the corresponding images. We show that our approach not only consistently leads to better image-model alignment, but also to improved 3D accuracy.
  arXiv  Detail & Related papers  (2024-03-18T10:13:53Z)
• DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis [18.64688172651478]
  We present DiffPortrait3D, a conditional diffusion model capable of synthesizing 3D-consistent photo-realistic novel views. Given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.
  arXiv  Detail & Related papers  (2023-12-20T13:31:11Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)
• Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
  We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
  arXiv  Detail & Related papers  (2022-04-21T03:42:31Z)
• Pixel Codec Avatars [99.36561532588831]
  Pixel Codec Avatars (PiCA) is a deep generative model of 3D human faces. On a single Oculus Quest 2 mobile VR headset, 5 avatars are rendered in realtime in the same scene.
  arXiv  Detail & Related papers  (2021-04-09T23:17:36Z)

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.