paper-with-me

Papers

VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization

2025-01-16 · Zixun Fang, Zhiheng Liu, Kai Zhu, Yu Liu, Ka Leong Cheng, Wei Zhai, Yang Cao, Zheng-Jun Zha

Video colorization aims to transform grayscale videos into vivid color representations while maintaining temporal consistency and structural integrity. Existing video colorization methods often suffer from color bleeding and lack comprehensive control, particularly under complex motion or diverse semantic cues. To this end, we introduce VanGogh, a unified multimodal diffusion-based framework for video colorization. VanGogh tackles these challenges using a Dual Qformer to align and fuse features from multiple modalities, complemented by a depth-guided generation process and an optical flow loss, which help reduce color overflow. Additionally, a color injection strategy and luma channel replacement are implemented to improve generalization and mitigate flickering artifacts. Thanks to this design, users can exercise both global and local control over the generation process, resulting in higher-quality colorized videos. Extensive qualitative and quantitative evaluations, and user studies, demonstrate that VanGogh achieves superior temporal consistency and color fidelity.Project page: https://becauseimbatman0.github.io/VanGogh.

📄 PDF Abstract BibTeX arXiv:2501.09499

Code (0)

등록된 구현이 없습니다.

Tasks

ColorizationOptical Flow Estimation

Methods 이 논문이 사용한 방법론

Colorization Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning

2025-11-22 · Xiaohong Liu, Xiufeng Song, Huayu Zheng, Lei Bai 외 arxiv

The proliferation of videos generated by diffusion models has raised increasing concerns about information security, highlighting the urgent need for reliable detection of synthetic media. Existing methods primarily focu…

Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing

2026-02-10 · Jialun Liu, Tian Li, Xiao Cao, Yukuo Ma 외 arxiv

Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and rely primarily on textual instructions, l…

Text-to-Video Generation

VINO: A Unified Visual Generator with Interleaved OmniModal Context

2026-01-05 · Junyi Chen, Tong He, Zhoujie Fu, Pengfei Wan 외 arxiv

We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a…

Instruction FollowingVideo Generation

X-Streamer: Unified Human World Modeling with Audiovisual Interaction

2025-09-25 · You Xie, Tianpei Gu, Zenan Li, Chenxu Zhang 외 arxiv

We introduce X-Streamer, an end-to-end multimodal human world modeling framework for building digital human agents capable of infinite interactions across text, speech, and video within a single unified architecture. Sta…

Bridging Video Understanding and Generation in a Unified Framework

2026-06-30 · Yuqi Wang, Runyi Li, Ruoyu Feng, Renjie Chen 외 arxiv

Recently, unified image generation and understanding have been extensively explored. However, extending such unified modeling paradigms to the video domain remains largely underexplored. A central challenge is that video…

Video GenerationImage Generation