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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Evaluating Robot Policies in a World Model
Video Signature: In-generation Watermarking for Latent Video Diffusion Models
STORK: Improving the Fidelity of Mid-NFE Sampling for Diffusion and Flow Matching Models
Interactive Video Generation via Domain Adaptation
UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation
DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds
MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
HyperMotion: DiT-Based Pose-Guided Human Image Animation of Complex Motions
MOVi: Training-free Text-conditioned Multi-Object Video Generation
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
RoboTransfer: Geometry-Consistent Video Diffusion for Robotic Visual Policy Transfer
VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models
VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
MAGREF: Masked Guidance for Any-Reference Video Generation
Learning World Models for Interactive Video Generation
PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
ATI: Any Trajectory Instruction for Controllable Video Generation
Minute-Long Videos with Dual Parallelisms
SageAttention2++: A More Efficient Implementation of SageAttention2
Think Before You Diffuse: LLMs-Guided Physics-Aware Video Generation
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
The Role of Video Generation in Enhancing Data-Limited Action Understanding
DriveCamSim: Generalizable Camera Simulation via Explicit Camera Modeling for Autonomous Driving
Dynamic-I2V: Exploring Image-to-Video Generaion Models via Multimodal LLM
MotionPro: A Precise Motion Controller for Image-to-Video Generation
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
WorldEval: World Model as Real-World Robot Policies Evaluator
SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation
From Single Images to Motion Policies via Video-Generation Environment Representations
ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos
DVD-Quant: Data-free Video Diffusion Transformers Quantization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.