Search Results for author:
Found 13 papers, 2 papers with code
Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video
Second, we introduce a novel loss to explicitly enforce consistency across generated views both in space and in time.
Coherent3D: Coherent 3D Portrait Video Reconstruction via Triplane Fusion
To this end, we propose a new fusion-based method that takes the best of both worlds by fusing a canonical 3D prior from a reference view with dynamic appearance from per-frame input views, producing temporally stable 3D videos with faithful reconstruction of the user's per-frame appearance.
BLADE: Single-view Body Mesh Learning through Accurate Depth Estimation
Extensive experiments on standard benchmarks and real-world close-range images show that our method is the first to accurately recover projection parameters from a single image, and consequently attain state-of-the-art accuracy on 3D pose estimation and 2D alignment for a wide range of images.
Coherent 3D Portrait Video Reconstruction via Triplane Fusion
Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, potentially democratizing telepresence.
Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling
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
Moreover, our discovery of natural information partition leads to a better understanding and manipulation of MLPs.
Learning Dynamic View Synthesis With Few RGBD Cameras
Experiments on the HTI dataset show that our method outperforms the baseline per-frame image fidelity and spatial-temporal consistency.
Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction
Reflective and textureless surfaces such as windows, mirrors, and walls can be a challenge for object and scene reconstruction.
Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering
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 #3 on
Generalizable Novel View Synthesis
on ZJU-MoCap
StereoDRNet: Dilated Residual Stereo Net
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.
Real-time 3D Face-Eye Performance Capture of a Person Wearing VR Headset
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.
3D Scanning Deformable Objects With a Single RGBD Sensor
We present a 3D scanning system for deformable objects that uses only a single Kinect sensor.
