https://github.com/nv-tlabs/GEN3C
공식 코드GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
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/nv-tlabs/cosmos-drive-dreams
공식 코드Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
https://github.com/nvidia/gr00t-dreams
공식 코드DreamGen: Unlocking Generalization in Robot Learning through Video World Models
https://github.com/nysp78/counterfactual-video-generation
공식 코드Causally Steered Diffusion for Automated Video Counterfactual Generation
https://github.com/oliverrensu/grat
공식 코드Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
https://github.com/oooolga/Ctrl-V
공식 코드Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion
https://github.com/oooolga/JEDi
공식 코드Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality
https://github.com/openai/consistency_models
공식 코드https://github.com/opendrivelab/vista
공식 코드Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
https://github.com/opengvlab/internvideo
공식 코드InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
https://github.com/opengvlab/phygenbench
공식 코드Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
https://github.com/opengvlab/vinci
공식 코드Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model
https://github.com/opennlplab/favdbench
공식 코드https://github.com/opennlplab/tavgbench
공식 코드https://github.com/opensparsellms/skip-dit
공식 코드https://github.com/orangesodahub/orv
공식 코드https://github.com/panpanfei/Bringing-a-Blurry-Frame-Alive-at-High-Frame-Rate-with-an-Event-Camera
공식 코드High Frame Rate Video Reconstruction based on an Event Camera
https://github.com/patrickrperrine/comp-choreo
공식 코드KP-RNN: A Deep Learning Pipeline for Human Motion Prediction and Synthesis of Performance Art
https://github.com/pengbo807/ConditionVideo
공식 코드ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation
https://github.com/pfnet-research/tgan2
공식 코드https://github.com/picsart-ai-research/streamingt2v
공식 코드StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
https://github.com/picsart-ai-research/text2video-zero
공식 코드Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
https://github.com/pierfrancescoardino/c2m
공식 코드Click to Move: Controlling Video Generation with Sparse Motion
https://github.com/pittisl/phyt2v
공식 코드PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
https://github.com/pku-alignment/safe-sora
공식 코드SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
https://github.com/pku-yuangroup/chronomagic-bench
공식 코드MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
https://github.com/pku-yuangroup/holotime
공식 코드HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
https://github.com/pku-yuangroup/magictime
공식 코드ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
https://github.com/pku-yuangroup/open-sora-plan
공식 코드OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model
https://github.com/pmh9960/spherediff
공식 코드https://github.com/pr-ryan/demo
공식 코드Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
https://github.com/pris-cv/cinetechbench
공식 코드CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
https://github.com/prototypenx/efficientmt
공식 코드EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
https://github.com/psh01087/Vid-ODE
공식 코드Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation
https://github.com/py85252876/mmvgm
공식 코드https://github.com/py85252876/uvd
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.