paper-with-me

Papers

LucidDream: Controlled Temporally-Consistent DeepDream on Videos

2019-11-27 · Joel Ruben Antony Moniz, Eunsu Kang, Barnabás Póczos

In this work, we aim to propose a set of techniques to improve the controllability and aesthetic appeal when DeepDream, which uses a pre-trained neural network to modify images by hallucinating objects into them, is applied to videos. In particular, we demonstrate a simple modification that improves control over the class of object that DeepDream is induced to hallucinate. We also show that the flickering artifacts which frequently appear when DeepDream is applied on videos can be mitigated by the use of an additional temporal consistency loss term.

📄 PDF Abstract BibTeX arXiv:1911.11960

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes

2023-11-22 · JaeYoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee 외

With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due…

Image GenerationScene Generation

Can Pose Transfer Models Generate Realistic Human Motion?

2025-01-26 · Vaclav Knapp, Matyas Bohacek

Recent pose-transfer methods aim to generate temporally consistent and fully controllable videos of human action where the motion from a reference video is reenacted by a new identity. We evaluate three state-of-the-art …

Pose Transfer

Developing Creative AI to Generate Sculptural Objects

2019-08-20 · Songwei Ge, Austin Dill, Eunsu Kang, Chun-Liang Li 외

We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical details of automatic art generation and the i…

ClusteringGenerating 3D Point Clouds

Finding Temporally Consistent Occlusion Boundaries in Videos using Geometric Context

2015-10-25 · S. Hussain Raza, Ahmad Humayun, Matthias Grundmann, David Anderson 외

We present an algorithm for finding temporally consistent occlusion boundaries in videos to support segmentation of dynamic scenes. We learn occlusion boundaries in a pairwise Markov random field (MRF) framework. We firs…

Region-Based Temporally Consistent Video Post-Processing

2015-06-01 · CVPR 2015 6 · Xuan Dong, Boyan Bonev, Yu Zhu, Alan L. Yuille

We study the problem of temporally consistent video post-processing. Previous post-processing algorithms usually either fail to keep high fidelity or fail to keep temporal consistency of output videos. In this paper, we …

Video Enhancement