We address the problem of aligning real-world 3D data of garments, which...
We present CaPhy, a novel method for reconstructing animatable human ava...
Learning-based approaches to monocular motion capture have recently show...
Reconstructing hand-held objects from monocular RGB images is an appeali...
Recent years have witnessed considerable achievements in editing images ...
We present AvatarReX, a new method for learning NeRF-based full-body ava...
Existing approaches to animatable NeRF-based head avatars are either bui...
Face reenactment methods attempt to restore and re-animate portrait vide...
Domain adaptation of 3D portraits has gained more and more attention.
Ho...
Creating animatable avatars from static scans requires the modeling of
c...
Naturally controllable human-scene interaction (HSI) generation has an
i...
Regression-based methods have shown high efficiency and effectiveness fo...
With NeRF widely used for facial reenactment, recent methods can recover...
We present Tensor4D, an efficient yet effective approach to dynamic scen...
3D-aware generative adversarial networks (GANs) synthesize high-fidelity...
We propose DiffuStereo, a novel system using only sparse cameras (8 in t...
We present FITE, a First-Implicit-Then-Explicit framework for modeling h...
We present PyMAF-X, a regression-based approach to recovering a full-bod...
Single-image human relighting aims to relight a target human under new
l...
In this paper, we present a Geometry-aware Neural Interpolation (Geo-NI)...
The advent of deep learning has led to significant progress in monocular...
Existing 3D-aware facial generation methods face a dilemma in quality ve...
Predicting human motion is critical for assistive robots and AR/VR
appli...
Existing state-of-the-art novel view synthesis methods rely on either fa...
It is extremely challenging to create an animatable clothed human avatar...
Graph convolutional network (GCN) has achieved great success in single h...
Estimating human pose and shape from monocular images is a long-standing...
We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural...
Previous portrait image generation methods roughly fall into two categor...
Cross-resolution image alignment is a key problem in multiscale gigapixe...
We introduce DoubleField, a novel representation combining the merits of...
Human volumetric capture is a long-standing topic in computer vision and...
We propose DeepMultiCap, a novel method for multi-person performance cap...
The light field (LF) reconstruction is mainly confronted with two challe...
Regression-based methods have recently shown promising results in
recons...
In this paper, a novel convolutional neural network (CNN)-based framewor...
Human pose transfer, which aims at transferring the appearance of a give...
We introduce VERTEX, an effective solution to recover 3D shape and intri...
The combination of various cameras is enriching the way of computational...
Garment representation, animation and editing is a challenging topic in ...
Deep implicit functions (DIFs), as a kind of 3D shape representation, ar...
Realistic speech-driven 3D facial animation is a challenging problem due...
We propose NormalGAN, a fast adversarial learning-based method to recons...
Modeling 3D humans accurately and robustly from a single image is very
c...
Learning-based light field reconstruction methods demand in constructing...
We introduce MulayCap, a novel human performance capture method using a
...
Recovering sharp video sequence from a motion-blurred image is highly
il...
In this paper, we propose an efficient method for robust 3D self-portrai...
This paper contributes a novel realtime multi-person motion capture algo...
This paper proposes a new method for simultaneous 3D reconstruction and
...