SOTAVerified

Video Generation

( Various Video Generation Tasks. Gif credit: MaGViT )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 1466 papers

TitleStatusHype
Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback LearningCode2
Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion TransformersCode2
I2V-Adapter: A General Image-to-Video Adapter for Diffusion ModelsCode2
Generative Inbetweening through Frame-wise Conditions-Driven Video GenerationCode2
Generative Diffusion Models on Graphs: Methods and ApplicationsCode2
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-DenoisingCode2
SF-V: Single Forward Video Generation ModelCode2
Generating Long Videos of Dynamic ScenesCode2
SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank AdaptationCode2
Conditional Image-to-Video Generation with Latent Flow Diffusion ModelsCode2
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral ConstraintsCode2
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene GenerationCode2
GenAI Arena: An Open Evaluation Platform for Generative ModelsCode2
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionCode2
RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera MovementsCode2
Concat-ID: Towards Universal Identity-Preserving Video SynthesisCode2
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in VideosCode2
I^2-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingCode2
FreeInit: Bridging Initialization Gap in Video Diffusion ModelsCode2
Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersCode2
Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion ModelCode2
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth GenerationCode2
Compositional Video Generation as Flow EqualizationCode2
Depth-Aware Generative Adversarial Network for Talking Head Video GenerationCode2
FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model EvaluationCode2
AnimateAnything: Fine-Grained Open Domain Image Animation with Motion GuidanceCode2
Collaborative Neural Rendering using Anime Character SheetsCode2
AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AICode2
Kandinsky 3.0 Technical ReportCode2
CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition AbilitiesCode2
Progressive Autoregressive Video Diffusion ModelsCode2
PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff DropCode2
PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video GenerationCode2
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion ModelsCode2
PresentAgent: Multimodal Agent for Presentation Video GenerationCode2
Promptus: Can Prompts Streaming Replace Video Streaming with Stable DiffusionCode2
Owl-1: Omni World Model for Consistent Long Video GenerationCode2
Panacea: Panoramic and Controllable Video Generation for Autonomous DrivingCode2
ORV: 4D Occupancy-centric Robot Video GenerationCode2
Phenaki: Variable Length Video Generation From Open Domain Textual DescriptionCode2
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative ModelsCode2
CelebV-Text: A Large-Scale Facial Text-Video DatasetCode2
CelebV-HQ: A Large-Scale Video Facial Attributes DatasetCode2
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion ModelsCode2
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationCode2
AR-Diffusion: Asynchronous Video Generation with Auto-Regressive DiffusionCode2
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsCode2
Neighboring Autoregressive Modeling for Efficient Visual GenerationCode2
DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image AnimationCode2
Omni-Video: Democratizing Unified Video Understanding and GenerationCode2
Show:102550
← PrevPage 5 of 30Next →
All datasetsUCF-101BAIR Robot PushingSky Time-lapseUCF-101 16 frames, 64x64, UnconditionalUCF-101 16 frames, Unconditional, Single GPULAION-400MTaichiUCF-101 16 frames, 128x128, UnconditionalKinetics-600 12 frames, 64x64How2SignKinetics-600 12 frames, 128x128Kinetics-600 48 frames, 64x64

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MCVDFVD162,460—Unverified
2VDMFVD161,396—Unverified
3TGAN-v2 (128x128)FVD161,209—Unverified
4MCVD (64x64)FVD161,143—Unverified
5MoCoGAN-HD (256x256, unconditional)FVD16700—Unverified
6MagicVideo (256x256, text-conditional)FVD16699—Unverified
7TATS (256x256)FVD16635—Unverified
8FIFO-DiffusionFVD128596.64—Unverified
9DIGAN (128x128, unconditional)FVD16577—Unverified
10LVDM (256x256, unconditional)FVD16552—Unverified
#ModelMetricClaimedVerifiedStatus
1MoCoGANFVD score503—Unverified
2Baseline (from LVT)FVD score320.9—Unverified
3SVG-FP (from FVD)FVD score315.5—Unverified
4CDNA (from FVD)FVD score296.5—Unverified
5SV2P (from FVD)FVD score262.5—Unverified
6SVG-LP (from vRNN)FVD score256.62—Unverified
7WAMFVD score159.6—Unverified
8VRNN 1LFVD score149.22—Unverified
9SAVP (from vRNN)FVD score143.43—Unverified
10Hier-VRNNFVD score143.4—Unverified
#ModelMetricClaimedVerifiedStatus
1MoCoGAN-HD (128x128)FVD 16183.6—Unverified
2TATS (128x128)FVD 16132.6—Unverified
3Long-video GAN (256x256)FVD 16116.5—Unverified
4DIGAN (128x128)FVD 16114.6—Unverified
5Long-video GAN (128x128)FVD 16107.5—Unverified
6LVDM (256x256)FVD 1695.2—Unverified
7DDMIFVD 1666.25—Unverified
8Latte + LeanVAEFVD 1649.59—Unverified
9StyleSV (256x256)FVD 1649—Unverified
#ModelMetricClaimedVerifiedStatus
1Video Diffusion ModelInception Score57—Unverified
2TGAN-ODEInception Score15.2—Unverified
3TGAN-FInception Score13.62—Unverified
4MoCoGANInception Score12.42—Unverified
5MoCoGAN-MDPInception Score11.86—Unverified
6TGAN-SVCInception Score11.85—Unverified
7VGANInception Score8.18—Unverified
#ModelMetricClaimedVerifiedStatus
1TGAN-FInception Score22.91—Unverified
2TGANv2Inception Score21.45—Unverified
3TGANv2-ODEInception Score21.02—Unverified
4MoCoGANInception Score12.42—Unverified
5MoCoGAN-MDPInception Score11.86—Unverified
6TGAN-SVCInception Score11.85—Unverified
7VGANInception Score8.18—Unverified
#ModelMetricClaimedVerifiedStatus
1Imagen original (constant=6)CLIP R-Precision92.12—Unverified
2Imagen fully distilled (oscillate (15,1))CLIP R-Precision90.97—Unverified
3Imagen distilled (constant=6)CLIP R-Precision90.88—Unverified
4Imagen original (oscillate(15,1))CLIP R-Precision89.91—Unverified
5Imagen fully distilled (constant=6)CLIP R-Precision89.68—Unverified
6Imagen distilled (oscillate (15,1))CLIP R-Precision88.78—Unverified
#ModelMetricClaimedVerifiedStatus
1DIGAN (256x256)FVD16156.7—Unverified
2MoCoGAN-HD (128x128)FVD16144.7—Unverified
3DIGAN (128x128)FVD16128.1—Unverified
4LVDM (256x256)FVD1699—Unverified
5TATS (128x128)FVD1694.6—Unverified
6StyleSV (256x256)FVD1682.6—Unverified
#ModelMetricClaimedVerifiedStatus
1TGANv2 (2020)Inception Score28.87—Unverified
2DVD-GANInception Score27.38—Unverified
3VideoGPTInception Score24.69—Unverified
4TGANv2Inception Score24.34—Unverified
5TGAN-FInception Score22.91—Unverified
6TGANv2-ODEInception Score21.02—Unverified
#ModelMetricClaimedVerifiedStatus
1DVD-GANFVD31.1—Unverified
2MAGVITFVD9.9—Unverified
#ModelMetricClaimedVerifiedStatus
1INR-VFVD16144—Unverified
#ModelMetricClaimedVerifiedStatus
1DVD-GANFID2.16—Unverified
#ModelMetricClaimedVerifiedStatus
1DVD-GANFID12.92—Unverified
#ModelMetricClaimedVerifiedStatus
1DiT-XL/2 + CVAE-FT-SEFID8.59—Unverified
#ModelMetricClaimedVerifiedStatus
1VideoAssembler (Zero-Shot, 256x256, class-conditional)FVD16252—Unverified
#ModelMetricClaimedVerifiedStatus
1PG-SWGAN-3DFID404.1—Unverified
#ModelMetricClaimedVerifiedStatus
1StyleSVFVD16207.2—Unverified