GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion

• URL: http://arxiv.org/abs/2412.10209v1
• Date: Fri, 13 Dec 2024 15:31:22 GMT
• Title: GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion
• Authors: Jiapeng Tang, Davide Davoli, Tobias Kirschstein, Liam Schoneveld, Matthias Niessner,
• Abstract summary: Photorealistic 3D head avatar reconstruction from recordings is challenging due to limited observations. We introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency. We demonstrate higher-fidelity avatar reconstructions from monocular videos captured on commodity devices.
• Score: 5.49003371165534
• License:
• Abstract: We propose a novel approach for reconstructing animatable 3D Gaussian avatars from monocular videos captured by commodity devices like smartphones. Photorealistic 3D head avatar reconstruction from such recordings is challenging due to limited observations, which leaves unobserved regions under-constrained and can lead to artifacts in novel views. To address this problem, we introduce a multi-view head diffusion model, leveraging its priors to fill in missing regions and ensure view consistency in Gaussian splatting renderings. To enable precise viewpoint control, we use normal maps rendered from FLAME-based head reconstruction, which provides pixel-aligned inductive biases. We also condition the diffusion model on VAE features extracted from the input image to preserve details of facial identity and appearance. For Gaussian avatar reconstruction, we distill multi-view diffusion priors by using iteratively denoised images as pseudo-ground truths, effectively mitigating over-saturation issues. To further improve photorealism, we apply latent upsampling to refine the denoised latent before decoding it into an image. We evaluate our method on the NeRSemble dataset, showing that GAF outperforms the previous state-of-the-art methods in novel view synthesis by a 5.34\% higher SSIM score. Furthermore, we demonstrate higher-fidelity avatar reconstructions from monocular videos captured on commodity devices.

Related papers

• NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model [57.92709692193132]
  NovelGS is a diffusion model for Gaussian Splatting given sparse-view images. We leverage the novel view denoising through a transformer-based network to generate 3D Gaussians.
  arXiv  Detail & Related papers  (2024-11-25T07:57:17Z)
• Generalizable and Animatable Gaussian Head Avatar [50.34788590904843]
  We propose Generalizable and Animatable Gaussian head Avatar (GAGAvatar) for one-shot animatable head avatar reconstruction. We generate the parameters of 3D Gaussians from a single image in a single forward pass. Our method exhibits superior performance compared to previous methods in terms of reconstruction quality and expression accuracy.
  arXiv  Detail & Related papers  (2024-10-10T14:29:00Z)
• LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors [34.91966359570867]
  sparse-view reconstruction is inherently ill-posed and under-constrained. We introduce LM-Gaussian, a method capable of generating high-quality reconstructions from a limited number of images. Our approach significantly reduces the data acquisition requirements compared to previous 3DGS methods.
  arXiv  Detail & Related papers  (2024-09-05T12:09:02Z)
• NPGA: Neural Parametric Gaussian Avatars [46.52887358194364]
  We propose a data-driven approach to create high-fidelity controllable avatars from multi-view video recordings. We build our method around 3D Gaussian splatting for its highly efficient rendering and to inherit the topological flexibility of point clouds. We evaluate our method on the public NeRSemble dataset, demonstrating that NPGA significantly outperforms the previous state-of-the-art avatars on the self-reenactment task by 2.6 PSNR.
  arXiv  Detail & Related papers  (2024-05-29T17:58:09Z)
• HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos [52.23323966700072]
  We present a framework for acquiring human avatars that are attached with high-resolution physically-based material textures and mesh from monocular video. Our method introduces a novel information fusion strategy to combine the information from the monocular video and synthesize virtual multi-view images. Experiments show that our approach outperforms previous representations in terms of high fidelity, and this explicit result supports deployment on common triangulars.
  arXiv  Detail & Related papers  (2024-05-18T11:49:09Z)
• SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior [53.52396082006044]
  Current methods struggle to maintain rendering quality at the viewpoint that deviates significantly from the training viewpoints. This issue stems from the sparse training views captured by a fixed camera on a moving vehicle. We propose a novel approach that enhances the capacity of 3DGS by leveraging prior from a Diffusion Model.
  arXiv  Detail & Related papers  (2024-03-29T09:20:29Z)
• Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction [60.52716381465063]
  We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality pseudo-observations. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times.
  arXiv  Detail & Related papers  (2023-05-24T14:00:32Z)
• High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors [29.293166730794606]
  We propose a new method for NeRF-based facial avatar reconstruction that utilizes 3D-aware generative prior. Compared with existing works, we obtain superior novel view synthesis results and faithfully face reenactment performance.
  arXiv  Detail & Related papers  (2022-11-28T04:49:46Z)
• LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space [90.74976459491303]
  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.
  arXiv  Detail & Related papers  (2022-03-15T13:22:57Z)

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.