Imagen de Portada

Latent Inter-Frame Pruning: A Training-Free Method Bridging Traditional Video Compression and Modern Diffusion Transformers for Efficient Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Menn, Dennis, Chou, Chih-Hsien
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
por: Menn, Dennis, et al.
Publicado: (2026)

Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions
por: Zhang, Xingguang, et al.
Publicado: (2024)

DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion
por: Hwang, Geunmin, et al.
Publicado: (2025)

FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
por: Le, Minh Khoa, et al.
Publicado: (2026)

TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
por: Lyu, Zonglin, et al.
Publicado: (2025)

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
por: Yuan, Zhihang, et al.
Publicado: (2025)

Latte: Latent Diffusion Transformer for Video Generation
por: Ma, Xin, et al.
Publicado: (2024)

Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention
por: Zhou, Xingyu, et al.
Publicado: (2024)

Similarity Trajectories: Linking Sampling Process to Artifacts in Diffusion-Generated Images
por: Menn, Dennis, et al.
Publicado: (2024)

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
por: Feng, X., et al.
Publicado: (2026)

Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models
por: Jang, Sangwon, et al.
Publicado: (2025)

RS-Prune: Training-Free Data Pruning at High Ratios for Efficient Remote Sensing Diffusion Foundation Models
por: Wei, Fan, et al.
Publicado: (2025)

Synthesizing Artifact Dataset for Pixel-level Detection
por: Menn, Dennis, et al.
Publicado: (2025)

Motion-aware Latent Diffusion Models for Video Frame Interpolation
por: Huang, Zhilin, et al.
Publicado: (2024)

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
por: Wang, Chenyu, et al.
Publicado: (2024)

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
por: Yu, Sihyun, et al.
Publicado: (2024)

F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis
por: Su, Sitong, et al.
Publicado: (2023)

Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence
por: Ling, Xiaoyue, et al.
Publicado: (2026)

ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation
por: Yang, Shaoshu, et al.
Publicado: (2024)

Token Pruning for In-Context Generation in Diffusion Transformers
por: Lin, Junqing, et al.
Publicado: (2026)

Training-Free Sketch-Guided Diffusion with Latent Optimization
por: Ding, Sandra Zhang, et al.
Publicado: (2024)

Temporal Aware Pruning for Efficient Diffusion-based Video Generation
por: Li, Sheng, et al.
Publicado: (2026)

Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
por: Li, Yize, et al.
Publicado: (2024)

Generative Video Compression with One-Dimensional Latent Representation
por: Zheng, Zihan, et al.
Publicado: (2026)

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
por: Chen, Pengtao, et al.
Publicado: (2024)

LDMVFI: Video Frame Interpolation with Latent Diffusion Models
por: Danier, Duolikun, et al.
Publicado: (2023)

Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priors
por: Chen, Yunuo, et al.
Publicado: (2026)

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
por: Yi, Jung, et al.
Publicado: (2025)

GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
por: Wang, Haonan, et al.
Publicado: (2024)

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame
por: Cao, Qinglong, et al.
Publicado: (2024)

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
por: Wang, Shaoguang, et al.
Publicado: (2025)

Generative Latent Video Compression
por: Guo, Zongyu, et al.
Publicado: (2025)

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models
por: Shi, Fengyuan, et al.
Publicado: (2023)

PARE: Pruning and Adaptive Routing for Efficient Video Generation
por: Wang, Yutong, et al.
Publicado: (2026)

Frame Interpolation with Consecutive Brownian Bridge Diffusion
por: Lyu, Zonglin, et al.
Publicado: (2024)

Latent-Compressed Variational Autoencoder for Video Diffusion Models
por: Guan, Jiarui, et al.
Publicado: (2026)

FreeInit: Bridging Initialization Gap in Video Diffusion Models
por: Wu, Tianxing, et al.
Publicado: (2023)

Training-Free Efficient Video Generation via Dynamic Token Carving
por: Zhang, Yuechen, et al.
Publicado: (2025)

Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers
por: Peng, Xinyu, et al.
Publicado: (2026)

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
por: Yesiltepe, Hidir, et al.
Publicado: (2026)