In this project, we propose a new learning based method consisting of DepthNet, PoseNet and Region Deformer Networks (RDN) to estimate depth from unconstrained monocular videos without ground truth supervision.

In this project, we aim at completely replacing the commonly used 3D convolutions to achieve fast inference speed while maintaining comparable accuracy.

We propose a new method for high-resolution optical flow estimation with significantly less computation, which is achieved by factorizing 2D optical flow with 1D attention and correlation.

For non-rigid registration, we propose RMA-Net to deform the input surface shape stage by stage. RMA-Net is totally trained in an unsupervised manner via our proposed multi-view 2D projection loss.

Recent work such as Sparse ICP achieves robustness via sparsity optimization at the cost of computational speed. In this paper, we propose a new method for robust registration with fast convergence.

In this project, we propose a formulation for robust non-rigid registration based on a globally smooth robust estimator for data fitting and regularization, which can handle outliers and partial overlaps. We apply the majorization-minimization algorithm to the problem, which reduces each iteration to solving a simple least-squares problem with L-BFGS.

In this project, we present a lightweight strategy that only requires sparse inputs or even a single image to recover high-fidelity face shapes with images captured under near-field lights.

This paper presents a novel face data generation method. Specifically, we render a large number of photo-realistic face images with different attributes based on inverse rendering. Furthermore, we construct a fine-detailed face image dataset by transferring different scales of details from one image to another.

Inspired by recent works in face animation from RGB-D or monocular video inputs, we develop a novel method for reconstructing 3D faces from unconstrained 2D images, using a coarse-to-fine optimization strategy.

While many caricatures are 2D images, this paper presents an algorithm for creating expressive 3D caricatures from 2D caricature images with a minimum of user interaction.

We propose a brand-new solution to this cross-domain expression transfer problem via nonlinear expression embedding and expression domain translation.

In this project, we propose a new CNN-based face recognition approach that incorporates such attributes into the training process.

To the best of our knowledge, this is the first work for automatic landmark detection and 3D face reconstruction for general caricatures.

In this project, we present a novel strategy to design disentangled 3D face shape representation.

We address the talking head problem with the aid of neural scene representation networks. The feature of audio is fed into a conditional implicit function to generate a dynamic neural radiance field for high-fidelity talking-head video synthesis.

In this project, we consider the problem to automatically reconstruct garment and body shapes from a single near-front view RGB image. To this end, we propose a layered garment representation on top of SMPL and novelly make the skinning weight of garment independent of the body mesh.

This project presents an autoencoder-like network architecture to learn disentangled shape and pose embedding specifically for the 3D human body.

We propose StereoPIFu, which integrates the geometric constraints of stereo vision with implicit function representation of PIFu, to recover the 3D shape of the clothed human.

In this project, we propose a parallel and scalable approach for geodesic distance computation on triangle meshes.

In this project, we note that the equivalence between ADMM and Douglas-Rachford splitting reveals that ADMM is in fact a fixed-point iteration in a lower-dimensional space. By applying Anderson acceleration to such lower-dimensional fixed-point iteration, we obtain a more effective approach for accelerating ADMM.

We propose a method to speed up ADMM using Anderson acceleration, an established technique for accelerating fixed-point iterations. We show that in the general case, ADMM is a fixed-point iteration of the second primal variable and the dual variable, and Anderson acceleration can be directly applied.

In this project, we propose a new geometry filtering technique called static/dynamic filter, which utilizes both static and dynamic guidances to achieve state-of-the-art results.

In this project, we propose a simple and effective technique to accelerate the convergence of local-global solvers.