paper-with-me

홈 › Papers

NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation

2024-05-23 · Chaokang Jiang, Dalong Du, Jiuming Liu, Siting Zhu, Zhenqiang Liu, Zhuang Ma, Zhujin Liang, Jie zhou

Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal information. This paper presents NeuroGauss4D-PCI, which excels at modeling complex non-rigid deformations across varied dynamic scenes. The method begins with an iterative Gaussian cloud soft clustering module, offering structured temporal point cloud representations. The proposed temporal radial basis function Gaussian residual utilizes Gaussian parameter interpolation over time, enabling smooth parameter transitions and capturing temporal residuals of Gaussian distributions. Additionally, a 4D Gaussian deformation field tracks the evolution of these parameters, creating continuous spatiotemporal deformation fields. A 4D neural field transforms low-dimensional spatiotemporal coordinates ($x,y,z,t$) into a high-dimensional latent space. Finally, we adaptively and efficiently fuse the latent features from neural fields and the geometric features from Gaussian deformation fields. NeuroGauss4D-PCI outperforms existing methods in point cloud frame interpolation, delivering leading performance on both object-level (DHB) and large-scale autonomous driving datasets (NL-Drive), with scalability to auto-labeling and point cloud densification tasks. The source code is released at https://github.com/jiangchaokang/NeuroGauss4D-PCI.

📄 PDF Abstract BibTeX arXiv:2405.14241

Code (1)

jiangchaokang/neurogauss4d-pci 공식 구현 pytorch

Tasks

Autonomous Driving

Similar Papers 제목 키워드 기반

DINE: Distance Is Not Enough -- Learning Global Deformation Priors for Robust Soft-Tissue Point Cloud Registration

2026-07-16 · Sara Monji-Azad, Rohit Beer, Marvin Kinz, Claudia Scherl 외 arxiv

Non-rigid point cloud registration is central to soft-tissue shape analysis, but large deformations, noise, and outliers make correspondence estimation challenging. Most learning-based methods rely on local objectives su…

Point Cloud Registration

TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

2024-04-23 · Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng 외

Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions…

Drivable 3D Gaussian Avatars

2023-11-14 · Wojciech Zielonka, Timur Bagautdinov, Shunsuke Saito, Michael Zollhöfer 외

We present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during trai…

3DGS

Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies

2021-05-06 · ICCV 2021 10 · Sida Peng, Junting Dong, Qianqian Wang, Shangzhan Zhang 외

This paper addresses the challenge of reconstructing an animatable human model from a multi-view video. Some recent works have proposed to decompose a non-rigidly deforming scene into a canonical neural radiance field an…

Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation

2024-06-09 · Vismay Modi, Nicholas Sharp, Or Perel, Shinjiro Sueda 외

The proliferation of 3D representations, from explicit meshes to implicit neural fields and more, motivates the need for simulators agnostic to representation. We present a data-, mesh-, and grid-free solution for elasti…