Second, we introduce a novel loss to explicitly enforce consistency across generated views both in space and in time.
We present a method that enables synthesizing novel views and novel poses of arbitrary human performers from sparse multi-view images.
Experiments on the HTI dataset show that our method outperforms the baseline per-frame image fidelity and spatial-temporal consistency.
Reflective and textureless surfaces such as windows, mirrors, and walls can be a challenge for object and scene reconstruction.
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.
Ranked #2 on Generalizable Novel View Synthesis on ZJU-MoCap
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.
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.