Papers with Code 아카이브
Video Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 16
- 보존된 평가 기록
- 130
<span style="color:grey; opacity: 0.6">( Various Video Generation Tasks. Gif credit: MaGViT )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bbzhu-jy16/motionvideogan
공식 코드MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs
https://github.com/belaalb/frameGAN
공식 코드https://github.com/benchcouncil/aigcbench
공식 코드AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI
https://github.com/bernhard2202/improved-video-gan
공식 코드Improving Video Generation for Multi-functional Applications
https://github.com/bilibili/index-anisora
공식 코드AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era
https://github.com/bioinf-jku/TTUR
공식 코드GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
https://github.com/bipashasen/INRV
공식 코드INR-V: A Continuous Representation Space for Video-based Generative Tasks
https://github.com/boese0601/magicdance
공식 코드MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion
https://github.com/boschresearch/VSTAR
공식 코드VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
https://github.com/boyazeng/weight_memorization
공식 코드Generative Modeling of Weights: Generalization or Memorization?
https://github.com/buggyyang/rvd
공식 코드https://github.com/bujiazi/motionclone
공식 코드MotionClone: Training-Free Motion Cloning for Controllable Video Generation
https://github.com/byeongjun-park/SteerX
공식 코드SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
https://github.com/bytedance/cascadev
공식 코드CascadeV: An Implementation of Wurstchen Architecture for Video Generation
https://github.com/carolineec/EverybodyDanceNow
공식 코드https://github.com/celebv-hq/celebv-hq
공식 코드https://github.com/changsn/FlexDiT
공식 코드FlexDiT: Dynamic Token Density Control for Diffusion Transformer
https://github.com/chaofantao/autoregressive-models-in-vision-survey
공식 코드https://github.com/chengyiliu-cs/generative-diffusion-models-on-graphs
공식 코드Generative Diffusion Models on Graphs: Methods and Applications
https://github.com/chenhaoxing/DeMamba
공식 코드DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
https://github.com/chenyanglei/all-in-one-deflicker
공식 코드Blind Video Deflickering by Neural Filtering with a Flawed Atlas
https://github.com/cjreinforce/jowa
공식 코드Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
https://github.com/da-group-pku/magic-1-for-1
공식 코드Magic 1-For-1: Generating One Minute Video Clips within One Minute
https://github.com/daooshee/hd-vg-130m
공식 코드Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation
https://github.com/davidpicard/homm
공식 코드PoM: Efficient Image and Video Generation with the Polynomial Mixer
https://github.com/dawn-lx/causal-videogen
공식 코드ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
https://github.com/dawn-lx/causalcache-vdm
공식 코드Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
https://github.com/degardinbruno/kinetic-gan
공식 코드Generative Adversarial Graph Convolutional Networks for Human Action Synthesis
https://github.com/delong-liu-bupt/ufo
공식 코드UFO: Enhancing Diffusion-Based Video Generation with a Uniform Frame Organizer
https://github.com/desaixie/pa_vdm
공식 코드https://github.com/diffusion-model-leiden/awesome-diffusion-models-for-tabular-data
공식 코드Diffusion Models for Tabular Data: Challenges, Current Progress, and Future Directions
https://github.com/dingyanb/mtvcrafter
공식 코드MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation
https://github.com/donydchen/mvsplat360
공식 코드MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
https://github.com/dualparal-project/dualparal
공식 코드https://github.com/dvlab-research/controlnext
공식 코드ControlNeXt: Powerful and Efficient Control for Image and Video Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.