3D Face Reconstruction

The DFDC (Deepfake Detection Challenge) is a dataset for deepface detection consisting of more than 100,000 videos. The DFDC dataset consists of two versions: - Preview dataset. with 5k videos. Featuring two facial modification algorithms. - Full dataset, with 124k videos. Featuring eight facial modification algorithms Source: The Deepfake Detection Challenge (DFDC) Preview Dataset

Aff-Wild is a large-scale in-the-wild dataset for valence-arousal estimation from videos with a variety of head poses, illumination conditions and occlusions. Source: Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond

The FER+ dataset is an extension of the original FER dataset, where the images have been re-labelled into one of 8 emotion types: neutral, happiness, surprise, sadness, anger, disgust, fear, and contempt. Source: https://github.com/Microsoft/FERPlus Image Source: https://github.com/Microsoft/FERPlus

AFLW2000-3D is a dataset of 2000 images that have been annotated with image-level 68-point 3D facial landmarks. This dataset is used for evaluation of 3D facial landmark detection models. The head poses are very diverse and often hard to be detected by a CNN-based face detector. Source: https://www.tensorflow.org/datasets/catalog/aflw2k3d Image Source: http://www.cbsr.ia.ac.cn/users/xiangyuzhu/projects/3DDFA/main.htm

The Oxford-BBC Lip Reading Sentences 2 (LRS2) dataset is one of the largest publicly available datasets for lip reading sentences in-the-wild. The database consists of mainly news and talk shows from BBC programs. Each sentence is up to 100 characters in length. The training, validation and test sets are divided according to broadcast date. It is a challenging set since it contains thousands of speakers without speaker labels and large variation in head pose. The pre-training set contains 96,318 utterances, the training set contains 45,839 utterances, the validation set contains 1,082 utterances and the test set contains 1,242 utterances. Source: Audio-visual Recognition of Overlapped speech for the LRS2 dataset Image Source: https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrs2.html

The Caltech Occluded Faces in the Wild (COFW) dataset is designed to present faces in real-world conditions. Faces show large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food, hands, microphones, etc.). All images were hand annotated using the same 29 landmarks as in LFPW. Both the landmark positions as well as their occluded/unoccluded state were annotated. The faces are occluded to different degrees, with large variations in the type of occlusions encountered. COFW has an average occlusion of over 23. Source: http://www.vision.caltech.edu/xpburgos/ICCV13/#dataset Image Source: http://www.vision.caltech.edu/xpburgos/ICCV13/#dataset

The Wider Facial Landmarks in the Wild or WFLW database contains 10000 faces (7500 for training and 2500 for testing) with 98 annotated landmarks. This database also features rich attribute annotations in terms of occlusion, head pose, make-up, illumination, blur and expressions. Source: Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion Image Source: https://wywu.github.io/projects/LAB/WFLW.html

The BP4D-Spontaneous dataset is a 3D video database of spontaneous facial expressions in a diverse group of young adults. Well-validated emotion inductions were used to elicit expressions of emotion and paralinguistic communication. Frame-level ground-truth for facial actions was obtained using the Facial Action Coding System. Facial features were tracked in both 2D and 3D domains using both person-specific and generic approaches. The database includes forty-one participants (23 women, 18 men). They were 18 – 29 years of age; 11 were Asian, 6 were African-American, 4 were Hispanic, and 20 were Euro-American. An emotion elicitation protocol was designed to elicit emotions of participants effectively. Eight tasks were covered with an interview process and a series of activities to elicit eight emotions. The database is structured by participants. Each participant is associated with 8 tasks. For each task, there are both 3D and 2D videos. As well, the Metadata include manually annotated action units (FACS AU), automatically tracked head pose, and 2D/3D facial landmarks. The database is in the size of about 2.6TB (without compression). Source: http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html Image Source: http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html

The VGG Face dataset is face identity recognition dataset that consists of 2,622 identities. It contains over 2.6 million images. Source: https://www.robots.ox.ac.uk/~vgg/data/vgg_face/ Image Source: http://www.bmva.org/bmvc/2015/papers/paper041/paper041.pdf

The JAFFE dataset consists of 213 images of different facial expressions from 10 different Japanese female subjects. Each subject was asked to do 7 facial expressions (6 basic facial expressions and neutral) and the images were annotated with average semantic ratings on each facial expression by 60 annotators. Source: Balanced k-Means and Min-Cut Clustering Image Source: https://www.researchgate.net/figure/Examples-of-facial-expression-images-from-the-JAFFE-database_fig11_51873190

FaceWarehouse is a 3D facial expression database that provides the facial geometry of 150 subjects, covering a wide range of ages and ethnic backgrounds. Source: 3D Face Reconstruction with Geometry Details from a Single Image

The MSU-MFSD dataset contains 280 video recordings of genuine and attack faces. 35 individuals have participated in the development of this database with a total of 280 videos. Two kinds of cameras with different resolutions (720×480 and 640×480) were used to record the videos from the 35 individuals. For the real accesses, each individual has two video recordings captured with the Laptop cameras and Android, respectively. For the video attacks, two types of cameras, the iPhone and Canon cameras were used to capture high definition videos on each of the subject. The videos taken with Canon camera were then replayed on iPad Air screen to generate the HD replay attacks while the videos recorded by the iPhone mobile were replayed itself to generate the mobile replay attacks. Photo attacks were produced by printing the 35 subjects’ photos on A3 papers using HP colour printer. The recording videos with respect to the 35 individuals were divided into training (15 subjects with 120 videos) and testing (40 subjects with 160 videos) datasets, respectively. Source: Enhance the Motion Cues for Face Anti-Spoofing using CNN-LSTM Architecture Image Source: face anti-spoofing based on color texture analysis

The Radboud Faces Database (RaFD) is a set of pictures of 67 models (both adult and children, males and females) displaying 8 emotional expressions. Source: http://www.socsci.ru.nl:8180/RaFD2/RaFD Image Source: http://www.socsci.ru.nl:8180/RaFD2/RaFD

The Oulu-CASIA NIR&VIS facial expression database consists of six expressions (surprise, happiness, sadness, anger, fear and disgust) from 80 people between 23 and 58 years old. 73.8% of the subjects are males. The subjects were asked to sit on a chair in the observation room in a way that he/ she is in front of camera. Camera-face distance is about 60 cm. Subjects were asked to make a facial expression according to an expression example shown in picture sequences. The imaging hardware works at the rate of 25 frames per second and the image resolution is 320 × 240 pixels. Source: Facial expression recognition from near-infrared videos Image Source: https://arxiv.org/abs/1712.03474

To the best of our knowledge this is the largest publicly available dataset of face images with gender and age labels for training. We provide pretrained models for both age and gender prediction.

To validate the racial bias of four commercial APIs and four state-of-the-art (SOTA) algorithms. Source: Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network

The Cross-Age Celebrity Dataset (CACD) contains 163,446 images from 2,000 celebrities collected from the Internet. The images are collected from search engines using celebrity name and year (2004-2013) as keywords. Therefore, it is possible to estimate the ages of the celebrities on the images by simply subtract the birth year from the year of which the photo was taken. Source: https://bcsiriuschen.github.io/CARC/ Image Source: https://www.pkuml.org/resources/pku-vehicleid.html

The MMI Facial Expression Database consists of over 2900 videos and high-resolution still images of 75 subjects. It is fully annotated for the presence of AUs in videos (event coding), and partially coded on frame-level, indicating for each frame whether an AU is in either the neutral, onset, apex or offset phase. A small part was annotated for audio-visual laughters. Source: https://mmifacedb.eu/ Image Source: https://mmifacedb.eu/

LFWA is a popular unconstrained facial attribute dataset, which consists of 13,143 facial images of 5,749 identities. Each facial image has 40 attribute annotations. Image Source: https://arxiv.org/pdf/1604.07360.pdf

FaceScape dataset provides 3D face models, parametric models and multi-view images in large-scale and high-quality. The camera parameters, the age and gender of the subjects are also included. The data have been released to public for non-commercial research purpose. Source: FaceScape

The Static Facial Expressions in the Wild (SFEW) dataset is a dataset for facial expression recognition. It was created by selecting static frames from the AFEW database by computing key frames based on facial point clustering. The most commonly used version, SFEW 2.0, was the benchmarking data for the SReco sub-challenge in EmotiW 2015. SFEW 2.0 has been divided into three sets: Train (958 samples), Val (436 samples) and Test (372 samples). Each of the images is assigned to one of seven expression categories, i.e., anger, disgust, fear, neutral, happiness, sadness, and surprise. The expression labels of the training and validation sets are publicly available, whereas those of the testing set are held back by the challenge organizer. Source: Deep Facial Expression Recognition: A Survey Image Source: https://computervisiononline.com/dataset/1105138659

VOCASET is a 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio. The dataset has 12 subjects and 480 sequences of about 3-4 seconds each with sentences chosen from an array of standard protocols that maximize phonetic diversity. Source: timzhang642

CASIA-MFSD is a dataset for face anti-spoofing. It contains 50 subjects, and 12 videos for each subject under different resolutions and light conditions. Three different spoof attacks are designed: replay, warp print and cut print attacks. The database contains 600 video recordings, in which 240 videos of 20 subjects are used for training and 360 videos of 30 subjects for testing. Source: Improving Face Anti-Spoofing by 3D Virtual Synthesis Image Source: https://link.springer.com/referenceworkentry/10.1007%2F978-1-4899-7488-4_9067

FGNet is a dataset for age estimation and face recognition across ages. It is composed of a total of 1,002 images of 82 people with age range from 0 to 69 and an age gap up to 45 years Source: Large age-gap face verification by feature injection in deep networks Image Source: https://www.researchgate.net/figure/Sample-images-from-the-FG-NET-Aging-database_fig1_220057621

SiW provides live and spoof videos from 165 subjects. For each subject, we have 8 live and up to 20 spoof videos, in total 4,478 videos. All videos are in 30 fps, about 15 second length, and 1080P HD resolution. The live videos are collected in four sessions with variations of distance, pose, illumination and expression. The spoof videos are collected with several attacks such as printed paper and replay.

WildDeepfake is a dataset for real-world deepfakes detection which consists of 7,314 face sequences extracted from 707 deepfake videos that are collected completely from the internet. WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop more effective detectors against real-world deepfakes. Source: https://github.com/deepfakeinthewild/deepfake-in-the-wild Image Source: https://github.com/deepfakeinthewild/deepfake-in-the-wild

Recently, facial expression recognition (FER) in the wild has gained a lot of researchers’ attention because it is a valuable topic to enable the FER techniques to move from the laboratory to the real applications. In this paper, we focus on this challenging but interesting topic and make contributions from three aspects. First, we present a new large-scale ’in-the-wild’ dynamic facial expression database, DFEW (Dynamic Facial Expression in the Wild), consisting of over 16,000 video clips from thousands of movies. These video clips contain various challenging interferences in practical scenarios such as extreme illumination, occlusions, and capricious pose changes. Second, we propose a novel method called ExpressionClustered Spatiotemporal Feature Learning (EC-STFL) framework to deal with dynamic FER in the wild. Third, we conduct extensive benchmark experiments on DFEW using a lot of spatiotemporal deep feature learning methods as well as our proposed EC-STFL. Experimental results show that DFEW is a well-designed and challenging database, and the proposed EC-STFL can promisingly improve the performance of existing spatiotemporal deep neural networks in coping with the problem of dynamic FER in the wild. Our DFEW database is publicly available and can be freely downloaded from https://dfew-dataset.github.io/.

Contains aesthetic scores and meaningful attributes assigned to each image by multiple human raters. Source: Photo Aesthetics Ranking Network with Attributes and Content Adaptation

CASIA-FASD is a small face anti-spoofing dataset containing 50 subjects. Source: Learning Generalizable and Identity-Discriminative Representations for Face Anti-Spoofing Image Source: https://arxiv.org/abs/1511.06316

The Expression in-the-Wild (ExpW) dataset is for facial expression recognition and contains 91,793 faces manually labeled with expressions. Each of the face images is annotated as one of the seven basic expression categories: “angry”, “disgust”, “fear”, “happy”, “sad”, “surprise”, or “neutral”.

Partial REID is a specially designed partial person reidentification dataset that includes 600 images from 60 people, with 5 full-body images and 5 occluded images per person. These images were collected on a university campus by 6 cameras from different viewpoints, backgrounds and different types of occlusion. The examples of partial persons in the Partial REID dataset are shown in the Figure. Source: Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification Image Source: https://arxiv.org/abs/1810.07399

The Florence 3D faces dataset consists of: * High-resolution 3D scans of human faces from many subjects. * Several video sequences of varying resolution, conditions and zoom level for each subject. Each subject is recorded in the following situations: * In a controlled setting in HD video. * In a less-constrained (but still indoor) setting using a standard, PTZ surveillance camera. * In an unconstrained, outdoor environment under challenging recording conditions. Source: https://www.micc.unifi.it/resources/datasets/florence-3d-faces/ Image Source: https://www.micc.unifi.it/resources/datasets/florence-3d-faces/

CelebV-HQ is a large-scale video facial attributes dataset with annotations. CelebV-HQ contains 35,666 video clips involving 15,653 identities and 83 manually labeled facial attributes covering appearance, action, and emotion. GitHub repository: https://github.com/celebv-hq/celebv-hq

The color FERET database is a dataset for face recognition. It contains 11,338 color images of size 512×768 pixels captured in a semi-controlled environment with 13 different poses from 994 subjects. Source: A Comprehensive Analysis of Deep Learning Based Representation for Face Recognition Image Source: https://www.researchgate.net/figure/Sample-results-taken-from-Color-FERET-data-set-testing-using-LBP-algorithm_fig4_308836179

The MAFL dataset contains manually annotated facial landmark locations for 19,000 training and 1,000 test images. Source: Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance Image Source: http://mmlab.ie.cuhk.edu.hk/projects/TCDCN.html

Matanga Darknet — 2025 Access Guide As internet censorship intensifies, Shadow Marketplaces remain crucial tools for anonymous transactions. Matanga Darknet is one of the most reliable platforms offering secure deals, wide product selection, and user-friendly interface. This article explains how to access Matanga Darknet, its advantages, and security measures for darknet operations. --- Current mirrors for Matanga Darknet Search engines may block darknet resources, so we've compiled official and backup mirrors: 1. Clearnet mirror (if Tor unavailable): > https://mat2web.top (use with VPN!) 2. Official .onion address (Tor Browser only): > http://matanzkgpadqndp44ysejfdwehmy4m22mzevmicoth6ebzequny6ayid.onion/ 3. Backup domain (if main domain blocked): > https://matangaweb.com/ (verified URL) Important! Always verify site's PGP signature and avoid phishing clones. Additional links|mirrors Download Tor Browser > https://www.torproject.org/download/ What is Matanga Darknet? Matanga Darknet is a darknet marketplace operating on the Escrow (escrow) model that guarantees transaction security. Key features: - Anonymous payments (BTC+LTC) - No KYC (no identity verification) - Seller rating system and honest reviews --- How to access Matanga Darknet? 1. Install Tor Browser (<download>from official site]). 2. Disable JavaScript in browser settings to prevent leaks. 3. Use only verified mirrors (listed above). --- Advantages of Matanga Darknet over other marketplaces ? Wide selection of high-quality products ? PGP encryption for communications ? Automatic seller payouts --- How to avoid scammers? - Verify .onion addresses through forums (Dread, Telegram channels) - Don't follow links from emails/messengers - Use hardware wallets (Ledger, Trezor) --- Future of darknet marketplaces With the development of decentralization technologies (Freenet, I2P), Matanga Darknet plans to implement: - Fully p2p trading without a central server - NFT-based transaction guarantees --- Useful links https://flagyl4people.top/matanga-tbilisi-1.php Conclusion Matanga Darknet remains one of the safest darknet marketplaces in 2025. Use only verified mirrors and practice good digital hygiene to avoid blocks and fraud Matanga Guru Matanga Tbilisi Matanga Georgia Matanga Shop Matanga Pro Matanga Matanga Guru Tbilisi Matanga Be Matanga Ge Matanga Shop Tbilisi Matanga Ru Matanga Org Matanga Me Matanga Be Matanga Drugs Matanga Cc Matanga Onion Link Matanga Pw Onion Matanga Top Matanga Грузия Matanga Be Tbilisi Matanga Org В Обход Matanga Org Matanga B Matanga Batumi Matanga Be В Обход Блокировки Matanga De Matanga Dijo La Changa Matanga Drugs Tbilisi Matanga Gru Matanga Gruzia Matanga Hill Matanga Onion Matanga Pro Регистрация Matanga Pv Matanga Pw Matanga Pw В Обход Блокировки Matanga Registration Matanga Tor Приложение Matanga A-Pvp Crystal Matanga Guru Analogi Matanga Guru Cache Matanga Pro Gde Naiti Nomer Matanga How To Buy Drag On Matanga Matanga Be Matanga Guru На Matanga Be Matanga Shop Matanga Be Matanga Bariga Matanga Chat Matanga Club Matanga Dark Web Matanga Drug Matanga Drugs Site Matanga Exy Matanga Game On Steam Matanga Georgia Canabis Matanga Godnotaba Matanga Guru Ru Matanga Kokain Matanga Link Matanga Live Matanga Marixuana Matanga Market Matanga Means In Bengali Matanga Narkotiki Matanga Onion Links Matanga Org Onion Matanga Pw Обход Matanga Register Matanga Registracia Matanga Rp Matanga Ru Union Matanga Russia Matanga Shop Georgia Matanga Sx Matanga Tor Link Matanga Url Matanga Найди Все То Что Искал Matanga Shop Biz Matanga Be Onion Matanga Be Santamaria123456 Matanga Br Matanga Bve Matanga Eb Matanga Ffun Matanga Fn Matanga Fun Matanga G Matanga Ge ????????? Matanga Grou Matanga Gru Matanga Gur Matanga Guru Batumi Matanga Guru Tbilisi Matanga Gurua Matanga Gururu Matanga Guruu Matanga Guu Matanga Nt Matanga Onins Matanga Oru Matanga Png Matanga Pro Registration Matanga Pron Matanga Prp Matanga Sx Matanga Union Matanga Uru Matanga Wp Matanga Ww Matanga Wwp Matanga Xs Org Matanga Apk Rash Matanga Registration Matanga Ruonion Matanga Sites Like Matanga Matanga Be Visitor Authorize