paper-with-me

Papers

Online Adaptation for Consistent Mesh Reconstruction in the Wild

2020-12-06 · NeurIPS 2020 12 · Xueting Li, Sifei Liu, Shalini De Mello, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz

This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D keypoints, or camera pose for each video frame, we pose video-based reconstruction as a self-supervised online adaptation problem applied to any incoming test video. We first learn a category-specific 3D reconstruction model from a collection of single-view images of the same category that jointly predicts the shape, texture, and camera pose of an image. Then, at inference time, we adapt the model to a test video over time using self-supervised regularization terms that exploit temporal consistency of an object instance to enforce that all reconstructed meshes share a common texture map, a base shape, as well as parts. We demonstrate that our algorithm recovers temporally consistent and reliable 3D structures from videos of non-rigid objects including those of animals captured in the wild -- an extremely challenging task rarely addressed before.

📄 PDF Abstract BibTeX arXiv:2012.03196

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Monocular 3D Object Reconstruction with GAN Inversion

2022-07-20 · Junzhe Zhang, Daxuan Ren, Zhongang Cai, Chai Kiat Yeo 외

Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the recons…

3D Object ReconstructionObjectObject Reconstruction

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

2020-04-04 · CVPR 2020 6 · Dominik Kulon, Riza Alp Güler, Iasonas Kokkinos, Michael Bronstein 외

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconst…

3D Hand Pose EstimationDecoderHand Pose EstimationPose Estimation

A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization

2023-10-04 · Kim Youwang, Lee Hyun, Kim Sung-Bin, Suekyeong Nam 외

We propose NeuFace, a 3D face mesh pseudo annotation method on videos via neural re-parameterized optimization. Despite the huge progress in 3D face reconstruction methods, generating reliable 3D face labels for in-the-w…

3D Face ReconstructionDiversityFace Reconstruction

Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction

2021-03-30 · CVPR 2021 1 · Shanyan Guan, Jingwei Xu, Yunbo Wang, Bingbing Ni 외

This paper considers a new problem of adapting a pre-trained model of human mesh reconstruction to out-of-domain streaming videos. However, most previous methods based on the parametric SMPL model \cite{loper2015smpl} un…

3D Human Pose Estimation

Mesh Density Adaptation for Template-based Shape Reconstruction

2023-07-30 · Yucheol Jung, Hyomin Kim, Gyeongha Hwang, Seung-Hwan Baek 외

In 3D shape reconstruction based on template mesh deformation, a regularization, such as smoothness energy, is employed to guide the reconstruction into a desirable direction. In this paper, we highlight an often overloo…

3D Shape ReconstructionInverse Rendering