Papers with Code 아카이브
3D Face Reconstruction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 9
- 보존된 평가 기록
- 94
3D Face Reconstruction is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.
<span style="color:grey; opacity: 0.6">( Image credit: 3DDFA_V2 )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/rshaojimmy/multimodal-deepfake
공식 코드https://github.com/rshaojimmy/seqdeepfake
공식 코드https://github.com/rub-syssec/generatedmediasurvey
공식 코드A Representative Study on Human Detection of Artificially Generated Media Across Countries
https://github.com/rub-syssec/wavefake
공식 코드https://github.com/ruijiezhu94/ti-face
공식 코드TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
https://github.com/ruizhe-l/tgb-gan
공식 코드https://github.com/ry85/Stochastic-Talking-Face-Generation-Using-Latent-Distribution-Matching
공식 코드Stochastic Talking Face Generation Using Latent Distribution Matching
https://github.com/ryanhe312/LatentFace
공식 코드A Generative Framework for Self-Supervised Facial Representation Learning
https://github.com/ryansteed/ieat
공식 코드Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
https://github.com/ryansteed/learning-appearance-bias
공식 코드A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild
https://github.com/sachith500/ContrastiveFaceRepresentation
공식 코드Multi-Dataset Benchmarks for Masked Identification using Contrastive Representation Learning
https://github.com/sahasubhajit/Speech-Spoofing-
공식 코드https://github.com/sahilg06/EmoGen
공식 코드https://github.com/saic-violet/bilayer-model
공식 코드Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars
https://github.com/sam575/axial-gan
공식 코드https://github.com/samir-atra/emotion_estimation_from_video_footage_with_lstm_ml_algorithm
공식 코드https://github.com/sanjaysaha1311/temporal-deepfake-segmentation
공식 코드https://github.com/sanoojan/reface
공식 코드Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models
https://github.com/sariyanidi/M3DFB
공식 코드3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation
https://github.com/sashankmvv/Emotion-recognition
공식 코드Facial Emotion Recognition: A multi-task approach using deep learning
https://github.com/sbelharbi/interpretable-fer-aus
공식 코드Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
https://github.com/sbelharbi/structured-output-ae
공식 코드Deep Neural Networks Regularization for Structured Output Prediction
https://github.com/sccsok/Locate-and-Verify
공식 코드Locate and Verify: A Two-Stream Network for Improved Deepfake Detection
https://github.com/sciencefans/Quality-Aware-Network
공식 코드https://github.com/sciencefans/RSA-for-object-detection
공식 코드https://github.com/sclbd/deepfakebench
공식 코드DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
https://github.com/scu-zjz/forensichub
공식 코드ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
https://github.com/searecluse/cvprw2024
공식 코드https://github.com/seasonSH/LiftedGAN
공식 코드https://github.com/seasonSH/Probabilistic-Face-Embeddings
공식 코드https://github.com/secml-lab-vt/EvolvingThreat-DeepfakeImageDetect
공식 코드An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
https://github.com/securifai/masked_faces
공식 코드A realistic approach to generate masked faces applied on two novel masked face recognition data sets
https://github.com/sefaburakokcu/finn-quantized-yolo
공식 코드https://github.com/semchan/HyperLips
공식 코드HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation
https://github.com/seva100/stylegan-for-facerec
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.