Search Results for author: Henry Fuchs

Found 10 papers, 2 papers with code

Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling

no code implementations10 Apr 2023 Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs

We present a method that enables synthesizing novel views and novel poses of arbitrary human performers from sparse multi-view images.

INV: Towards Streaming Incremental Neural Videos

no code implementations3 Feb 2023 Shengze Wang, Alexey Supikov, Joshua Ratcliff, Henry Fuchs, Ronald Azuma

Moreover, our discovery of natural information partition leads to a better understanding and manipulation of MLPs.

Learning Dynamic View Synthesis With Few RGBD Cameras

no code implementations22 Apr 2022 Shengze Wang, Youngjoong Kwon, Yuan Shen, Qian Zhang, Andrei State, Jia-Bin Huang, Henry Fuchs

Experiments on the HTI dataset show that our method outperforms the baseline per-frame image fidelity and spatial-temporal consistency.

Novel View Synthesis

Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction

no code implementations5 Oct 2021 Justin Wilson, Nicholas Rewkowski, Ming C. Lin, Henry Fuchs

Reflective and textureless surfaces such as windows, mirrors, and walls can be a challenge for object and scene reconstruction.

3D Reconstruction 3D Scene Reconstruction +3

Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering

1 code implementation NeurIPS 2021 Youngjoong Kwon, Dahun Kim, Duygu Ceylan, Henry Fuchs

To tackle this, we propose Neural Human Performer, a novel approach that learns generalizable neural radiance fields based on a parametric human body model for robust performance capture.

Generalizable Novel View Synthesis

StereoDRNet: Dilated Residual Stereo Net

no code implementations3 Apr 2019 Rohan Chabra, Julian Straub, Chris Sweeney, Richard Newcombe, Henry Fuchs

We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene.

3D Reconstruction

Real-time 3D Face-Eye Performance Capture of a Person Wearing VR Headset

no code implementations21 Jan 2019 Guoxian Song, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, Juyong Zhang, Henry Fuchs

Teleconference or telepresence based on virtual reality (VR) headmount display (HMD) device is a very interesting and promising application since HMD can provide immersive feelings for users.

Cannot find the paper you are looking for? You can Submit a new open access paper.