paper-with-me

Papers

Enabling Visual Composition and Animation in Unsupervised Video Generation

2024-03-21 · Aram Davtyan, Sepehr Sameni, Björn Ommer, Paolo Favaro

In this work we propose a novel method for unsupervised controllable video generation. Once trained on a dataset of unannotated videos, at inference our model is capable of both composing scenes of predefined object parts and animating them in a plausible and controlled way. This is achieved by conditioning video generation on a randomly selected subset of local pre-trained self-supervised features during training. We call our model CAGE for visual Composition and Animation for video GEneration. We conduct a series of experiments to demonstrate capabilities of CAGE in various settings. Project website: https://araachie.github.io/cage.

📄 PDF Abstract BibTeX arXiv:2403.14368

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Unsupervised Volumetric Animation

2023-01-26 · CVPR 2023 1 · Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Kyle Olszewski 외

We propose a novel approach for unsupervised 3D animation of non-rigid deformable objects. Our method learns the 3D structure and dynamics of objects solely from single-view RGB videos, and can decompose them into semant…

3D geometryKeypoint EstimationNovel View Synthesis

Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation

2024-08-29 · Xiaoyu Jin, Zunnan Xu, Mingwen Ou, Wenming Yang

Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images. Despite advancements, maintaining appearance consistency in animations re…

AllVideo Generation

FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations

2024-11-16 · CVPR 2025 1 · Hmrishav Bandyopadhyay, Yi-Zhe Song

Sketch animations offer a powerful medium for visual storytelling, from simple flip-book doodles to professional studio productions. While traditional animation requires teams of skilled artists to draw key frames and in…

Visual Storytelling

Dormant: Defending against Pose-driven Human Image Animation

2024-09-22 · Jiachen Zhou, Mingsi Wang, Tianlin Li, Guozhu Meng 외

Pose-driven human image animation has achieved tremendous progress, enabling the generation of vivid and realistic human videos from just one single photo. However, it conversely exacerbates the risk of image misuse, as …

Image AnimationVideo Generation

DATAREEL: Automated Data-Driven Video Story Generation with Animations

2026-04-28 · Ridwan Mahbub, Syem Aziz, Mahir Ahmed, Shadikur Rahman 외 arxiv

Data videos are a powerful medium for visual data based storytelling, combining animated, chart-centric visualizations with synchronized narration. Widely used in journalism, education, and public communication, they hel…

Story Generation