Zobrazeno 1 - 10
of 272
pro vyhledávání: '"Singh, Krishna Kumar"'
Autor:
Pan, Boxiao, Xu, Zhan, Huang, Chun-Hao Paul, Singh, Krishna Kumar, Zhou, Yang, Guibas, Leonidas J., Yang, Jimei
Generating video background that tailors to foreground subject motion is an important problem for the movie industry and visual effects community. This task involves synthesizing background that aligns with the motion and appearance of the foreground
Externí odkaz:
http://arxiv.org/abs/2401.10822
Autor:
Li, Nannan, Liu, Qing, Singh, Krishna Kumar, Wang, Yilin, Zhang, Jianming, Plummer, Bryan A., Lin, Zhe
Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement from learning
Externí odkaz:
http://arxiv.org/abs/2312.14985
Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. Thi
Externí odkaz:
http://arxiv.org/abs/2312.06712
Autor:
Zhu, Zhen, Li, Yijun, Lyu, Weijie, Singh, Krishna Kumar, Shu, Zhixin, Pirk, Soeren, Hoiem, Derek
We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the
Externí odkaz:
http://arxiv.org/abs/2307.01425
Autor:
Kulal, Sumith, Brooks, Tim, Aiken, Alex, Wu, Jiajun, Yang, Jimei, Lu, Jingwan, Efros, Alexei A., Singh, Krishna Kumar
We study the problem of inferring scene affordances by presenting a method for realistically inserting people into scenes. Given a scene image with a marked region and an image of a person, we insert the person into the scene while respecting the sce
Externí odkaz:
http://arxiv.org/abs/2304.14406
Autor:
Cho, Wonwoong, Ravi, Hareesh, Harikumar, Midhun, Khuc, Vinh, Singh, Krishna Kumar, Lu, Jingwan, Inouye, David I., Kale, Ajinkya
Denoising Diffusion models have shown remarkable capabilities in generating realistic, high-quality and diverse images. However, the extent of controllability during generation is underexplored. Inspired by techniques based on GAN latent space for im
Externí odkaz:
http://arxiv.org/abs/2302.14368
We present multimodal conditioning modules (MCM) for enabling conditional image synthesis using pretrained diffusion models. Previous multimodal synthesis works rely on training networks from scratch or fine-tuning pretrained networks, both of which
Externí odkaz:
http://arxiv.org/abs/2302.12764
Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is hard
Externí odkaz:
http://arxiv.org/abs/2302.03027
Autor:
Jain, Rishabh, Hemani, Mayur, Ceylan, Duygu, Singh, Krishna Kumar, Lu, Jingwan, Sarkar, Mausoom, Krishnamurthy, Balaji
Numerous pose-guided human editing methods have been explored by the vision community due to their extensive practical applications. However, most of these methods still use an image-to-image formulation in which a single image is given as input to p
Externí odkaz:
http://arxiv.org/abs/2211.10157
Autor:
Jain, Rishabh, Singh, Krishna Kumar, Hemani, Mayur, Lu, Jingwan, Sarkar, Mausoom, Ceylan, Duygu, Krishnamurthy, Balaji
The task of human reposing involves generating a realistic image of a person standing in an arbitrary conceivable pose. There are multiple difficulties in generating perceptually accurate images, and existing methods suffer from limitations in preser
Externí odkaz:
http://arxiv.org/abs/2211.08540