Google Brain proposed MLP-Mixer (code is available in google-research/vision_transformer official) which solely used multi-perceptron network (MLP) for computer vision tasks. This is different most commonly used convolution neural network (CNN) or more recently transformer based approaches. The experiment on image classification indicates that, given sufficient amount of data (e.g., 100M images) for pre-training then fine-tuned for target task (ImageNet 2012), MLP-Mixer is able to achieve competitive result as CNN and transformer. However, the performance drops far belower than CNN when insufficient amount of data are available for pre-training, especially for its larger variation. It is also found at similar accuracy, MLP-Mixer and transformer are faster than CNN (ResNet) for inference and training by 2~3 times.

This is my reading note for GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction. The code is available in GANFit. GANFit reconstructs high quality texture and geometry from a single image with precise identity recovery. To do this, it utilizes GANs to train a very powerful generator of facial texture in UV space. Then, it revisits the original 3D Morphable Models (3DMMs) fitting approaches making use of non-linear optimization to find the optimal latent parameters that best reconstruct the test image but under a new perspective. It optimizes the parameters with the supervision of pretrained deep identity features through our end-to-end differentiable framework.

An operating expense (OPEX) is an expense required for the day-to-day functioning of a business. In contrast, a capital expense (CAPEX) is an expense a business incurs to create a benefit in the future. Operating expenses and capital expenses are treated quite differently for accounting and tax purposes. This note is based on my reading of The Difference Between an Operating Expense vs. a Capital Expense

This is reading note for Avatarme: Realistically renderable 3d facial reconstruction ‘in-The-wild’, which was published in CVPR 2020 and code is available in github. Avatarme aims to reconstruct photorealistic 3D faces from a single “in-the-wild” image with an increasing level of detail. It could generate 4K by 6K-resolution 3D faces from a single low-resolution image that, for the first time, bridges the uncanny valley.

Note this website is based on work from The World History and Atlas. There is a version with 3D map in 历史时间线.

This notebooks describes the models which could represent animatable 3D face mesh, which is usually referred 3D morphorble model (3DMM).

This is my reading note for Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision (code). The paper is also called RingNet and was published in CVPR 2019. The paper solves the problems of 3D face reconstruction from a single 2D image and the training requires no 3D ground truth. To this end, RingNet leverages multiple images of a person and automatically detected 2D face features. It uses a novel loss that encourages the face shape to be similar when the identity is the same and different for different people. This is based on observation that an individual’s face shape is constant across images, regardless of expres- sion, pose, lighting, etc.

This post compares three stocks in estate: Redfin, Zillow and OpenDoor. I try to use the their 2020’s earning report for my analysis.

This is my reading note for paper Learning an Animatable Detailed 3D Face Model from In-The-Wild Images and code is available in DECA. The paper proposed method for producing animatable detailed 3D face model from uncontrolled image datasets. For uncontrolled, it means no control light settings and camera view angles are required; however it does require the dataset contains multiple images for each subjets.

This is my reading note for RMPE: Regional Multi-person Pose Estimation and the code is available at MVIG-SJTU/AlphaPose. This paper is a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. The framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG).