In this paper we present ADOP, a novel point-based, differentiable neural rendering pipeline. Like other neural renderers, our system takes as input calibrated camera images …
S Hu, T Hu, Z Liu - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We present GauHuman a 3D human model with Gaussian Splatting for both fast training (1 2 minutes) and real-time rendering (up to 189 FPS) compared with existing NeRF-based …
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We …
View synthesis allows for the generation of new views of a scene given one or more images. This is challenging; it requires comprehensively understanding the 3D scene from images …
We present a new point-based approach for modeling the appearance of real scenes. The approach uses a raw point cloud as the geometric representation of a scene, and augments …
Y Jiang, D Ji, Z Han, M Zwicker - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDFs) …
B Cui, W Tao, H Zhao - Remote Sensing, 2021 - mdpi.com
Three-dimensional reconstruction technology has demonstrated broad application potential in the industrial, construction, medical, forestry, agricultural, and pastural sectors in the last …
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 …
X Xu, L Siyao, W Sun, Q Yin… - Advances in Neural …, 2019 - proceedings.neurips.cc
Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors. Existing video interpolation methods usually assume …