Cover Image

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Ziyun, Lin, Yiqi, Liang, Guoqiang, Shou, Mike Zheng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
by: Lin, Yiqi, et al.
Published: (2026)

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
by: Chen, Joya, et al.
Published: (2025)

Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
by: Zeng, Ziyun, et al.
Published: (2025)

VideoGUI: A Benchmark for GUI Automation from Instructional Videos
by: Lin, Kevin Qinghong, et al.
Published: (2024)

VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning
by: Liu, Ye, et al.
Published: (2025)

Parrot Captions Teach CLIP to Spot Text
by: Lin, Yiqi, et al.
Published: (2023)

Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
by: Wang, Jiaqi, et al.
Published: (2025)

Factorized Learning for Temporally Grounded Video-Language Models
by: Zeng, Wenzheng, et al.
Published: (2025)

Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
by: Wu, Song, et al.
Published: (2026)

Paper2Video: Automatic Video Generation from Scientific Papers
by: Zhu, Zeyu, et al.
Published: (2025)

PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
by: Gao, Heyuan, et al.
Published: (2026)

H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
by: Ci, Hai, et al.
Published: (2025)

Code2Video: A Code-centric Paradigm for Educational Video Generation
by: Chen, Yanzhe, et al.
Published: (2025)

Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator
by: Zhao, Henry Hengyuan, et al.
Published: (2023)

Olaf-World: Orienting Latent Actions for Video World Modeling
by: Jiang, Yuxin, et al.
Published: (2026)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
by: Gu, Yuchao, et al.
Published: (2026)

An Inpainting-Infused Pipeline for Attire and Background Replacement
by: Perche-Mahlow, Felipe Rodrigues, et al.
Published: (2024)

In-Context Learning with Unpaired Clips for Instruction-based Video Editing
by: Liao, Xinyao, et al.
Published: (2025)

One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
by: Bai, Zechen, et al.
Published: (2024)

Less is More: Label-Guided Summarization of Procedural and Instructional Videos
by: Rajpal, Shreya, et al.
Published: (2026)

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

ShowUI-$π$: Flow-based Generative Models as GUI Dexterous Hands
by: Hu, Siyuan, et al.
Published: (2025)

SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
by: Zhao, Henry Hengyuan, et al.
Published: (2023)

ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Model
by: Xu, Hongbin, et al.
Published: (2024)

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
by: Wang, Zun, et al.
Published: (2025)

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
by: Liu, Xianjie, et al.
Published: (2025)

Boximator: Generating Rich and Controllable Motions for Video Synthesis
by: Wang, Jiawei, et al.
Published: (2024)

Resource-Efficient Motion Control for Video Generation via Dynamic Mask Guidance
by: Feng, Sicong, et al.
Published: (2025)

DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance
by: Shen, Xuan, et al.
Published: (2025)

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
by: Deng, Yufan, et al.
Published: (2025)

CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography
by: Li, Si, et al.
Published: (2026)

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
by: Ji, Yicheng, et al.
Published: (2025)

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning
by: Zeng, Xingchen, et al.
Published: (2024)

The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
by: Hu, Siyuan, et al.
Published: (2024)

TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation
by: Li, Ruineng, et al.
Published: (2025)

MCIE: Multimodal LLM-Driven Complex Instruction Image Editing with Spatial Guidance
by: Bai, Xuehai, et al.
Published: (2026)

YTCommentQA: Video Question Answerability in Instructional Videos
by: Yang, Saelyne, et al.
Published: (2024)

Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation
by: Liu, Jinlin, et al.
Published: (2024)

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
by: Yang, Zhenyu, et al.
Published: (2025)

VideoMaMa: Mask-Guided Video Matting via Generative Prior
by: Lim, Sangbeom, et al.
Published: (2026)