DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting

• URL: http://arxiv.org/abs/2504.10486v1
• Date: Mon, 14 Apr 2025 17:59:58 GMT
• Title: DNF-Avatar: Distilling Neural Fields for Real-time Animatable Avatar Relighting
• Authors: Zeren Jiang, Shaofei Wang, Siyu Tang,
• Abstract summary: Creating relightable and an computationable human avatars from monocular videos is a rising research topic with a range of applications.<n>Previous works utilize neural fields together with physically based rendering (PBR), to estimate geometry and disentangle appearance properties of human avatars.<n>To tackle this problem, we proposed to distill the knowledge from implicit neural fields to explicit 2D Gaussian splatting representation.
• Score: 12.917419616798815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Creating relightable and animatable human avatars from monocular videos is a rising research topic with a range of applications, e.g. virtual reality, sports, and video games. Previous works utilize neural fields together with physically based rendering (PBR), to estimate geometry and disentangle appearance properties of human avatars. However, one drawback of these methods is the slow rendering speed due to the expensive Monte Carlo ray tracing. To tackle this problem, we proposed to distill the knowledge from implicit neural fields (teacher) to explicit 2D Gaussian splatting (student) representation to take advantage of the fast rasterization property of Gaussian splatting. To avoid ray-tracing, we employ the split-sum approximation for PBR appearance. We also propose novel part-wise ambient occlusion probes for shadow computation. Shadow prediction is achieved by querying these probes only once per pixel, which paves the way for real-time relighting of avatars. These techniques combined give high-quality relighting results with realistic shadow effects. Our experiments demonstrate that the proposed student model achieves comparable or even better relighting results with our teacher model while being 370 times faster at inference time, achieving a 67 FPS rendering speed.

Related papers

• LightAvatar: Efficient Head Avatar as Dynamic Neural Light Field [58.93692943064746]
  We introduce LightAvatar, the first head avatar model based on neural light fields (NeLFs) LightAvatar renders an image from 3DMM parameters and a camera pose via a single network forward pass, without using mesh or volume rendering.
  arXiv  Detail & Related papers  (2024-09-26T17:00:02Z)
• Interactive Rendering of Relightable and Animatable Gaussian Avatars [37.73483372890271]
  We propose a simple and efficient method to decouple body materials and lighting from multi-view or monocular avatar videos. Our method can render higher quality results at a faster speed on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-07-15T13:25:07Z)
• Splatter Image: Ultra-Fast Single-View 3D Reconstruction [67.96212093828179]
  Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images. We learn a neural network that, at test time, performs reconstruction in a feed-forward manner, at 38 FPS. On several synthetic, real, multi-category and large-scale benchmark datasets, we achieve better results in terms of PSNR, LPIPS, and other metrics while training and evaluating much faster than prior works.
  arXiv  Detail & Related papers  (2023-12-20T16:14:58Z)
• 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting [32.63571465495127]
  We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS) We learn a non-rigid network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS) Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input.
  arXiv  Detail & Related papers  (2023-12-14T18:54:32Z)
• ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering [62.81677824868519]
  We propose an animatable Gaussian splatting approach for photorealistic rendering of dynamic humans in real-time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.
  arXiv  Detail & Related papers  (2023-12-10T17:07:37Z)
• FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding [33.03011612052884]
  FlashAvatar is a novel and lightweight 3D animatable avatar representation. It can reconstruct a digital avatar from a short monocular video sequence in minutes. It can render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU.
  arXiv  Detail & Related papers  (2023-12-03T07:23:53Z)
• FLARE: Fast Learning of Animatable and Relightable Mesh Avatars [64.48254296523977]
  Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. We introduce FLARE, a technique that enables the creation of animatable and relightable avatars from a single monocular video.
  arXiv  Detail & Related papers  (2023-10-26T16:13:00Z)
• Towards Practical Capture of High-Fidelity Relightable Avatars [60.25823986199208]
  TRAvatar is trained with dynamic image sequences captured in a Light Stage under varying lighting conditions. It can predict the appearance in real-time with a single forward pass, achieving high-quality relighting effects. Our framework achieves superior performance for photorealistic avatar animation and relighting.
  arXiv  Detail & Related papers  (2023-09-08T10:26:29Z)
• 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)

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.