Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Han, Junlin"'
Autor:
Yang, Ling, Zhang, Zixiang, Han, Junlin, Zeng, Bohan, Li, Runjia, Torr, Philip, Zhang, Wentao
Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized through S
Externí odkaz:
http://arxiv.org/abs/2410.09009
Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed by a feed-f
Externí odkaz:
http://arxiv.org/abs/2410.00890
Autor:
Li, Runjia, Han, Junlin, Melas-Kyriazi, Luke, Sun, Chunyi, An, Zhaochong, Gui, Zhongrui, Sun, Shuyang, Torr, Philip, Jakab, Tomas
We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often struggle with this generation task due to a limited understanding of p
Externí odkaz:
http://arxiv.org/abs/2409.08271
Autor:
Wang, Fangjinhua, Zhu, Qingtian, Chang, Di, Gao, Quankai, Han, Junlin, Zhang, Tong, Hartley, Richard, Pollefeys, Marc
3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving and robotics. Leveraging multiple views of a scene captured from dif
Externí odkaz:
http://arxiv.org/abs/2408.15235
This paper presents a novel method for building scalable 3D generative models utilizing pre-trained video diffusion models. The primary obstacle in developing foundation 3D generative models is the limited availability of 3D data. Unlike images, text
Externí odkaz:
http://arxiv.org/abs/2403.12034
Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain certain degrada
Externí odkaz:
http://arxiv.org/abs/2403.10520
In the pursuit of efficient automated content creation, procedural generation, leveraging modifiable parameters and rule-based systems, emerges as a promising approach. Nonetheless, it could be a demanding endeavor, given its intricate nature necessi
Externí odkaz:
http://arxiv.org/abs/2310.12945
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analysis of the audio-visual data reveals a large degree of hyperbolicity,
Externí odkaz:
http://arxiv.org/abs/2308.12558
We present NeRFEditor, an efficient learning framework for 3D scene editing, which takes a video captured over 360{\deg} as input and outputs a high-quality, identity-preserving stylized 3D scene. Our method supports diverse types of editing such as
Externí odkaz:
http://arxiv.org/abs/2212.03848
Autor:
Han, Junlin, Zhan, Huangying, Hong, Jie, Fang, Pengfei, Li, Hongdong, Petersson, Lars, Reid, Ian
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence. Firstly, we propose a self-supervised machine memory quantification pipeline, dubbed ``Ma
Externí odkaz:
http://arxiv.org/abs/2211.07625