Zobrazeno 1 - 10
of 109
pro vyhledávání: '"ACUNA, DAVID"'
Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains underexplored. In th
Externí odkaz:
http://arxiv.org/abs/2409.09788
Autor:
Liang, Ruofan, Gojcic, Zan, Nimier-David, Merlin, Acuna, David, Vijaykumar, Nandita, Fidler, Sanja, Wang, Zian
The correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process. While recent large-scale diffusion models have shown strong
Externí odkaz:
http://arxiv.org/abs/2408.09702
Autor:
Mirzaei, Ashkan, De Lutio, Riccardo, Kim, Seung Wook, Acuna, David, Kelly, Jonathan, Fidler, Sanja, Gilitschenski, Igor, Gojcic, Zan
Neural reconstruction approaches are rapidly emerging as the preferred representation for 3D scenes, but their limited editability is still posing a challenge. In this work, we propose an approach for 3D scene inpainting -- the task of coherently rep
Externí odkaz:
http://arxiv.org/abs/2404.10765
Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying the training recipes. In this work, we venture into an orthogonal direct
Externí odkaz:
http://arxiv.org/abs/2404.06510
Autor:
Li, Daiqing, Ling, Huan, Kar, Amlan, Acuna, David, Kim, Seung Wook, Kreis, Karsten, Torralba, Antonio, Fidler, Sanja
In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative model into st
Externí odkaz:
http://arxiv.org/abs/2307.07487
Autor:
Prabhu, Viraj, Acuna, David, Liao, Andrew, Mahmood, Rafid, Law, Marc T., Hoffman, Judy, Fidler, Sanja, Lucas, James
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domain. However, for high-stakes applications (e.g. autonomous driving), it
Externí odkaz:
http://arxiv.org/abs/2302.04832
Publikováno v:
ECCV 2022
We consider the challenging problem of outdoor lighting estimation for the goal of photorealistic virtual object insertion into photographs. Existing works on outdoor lighting estimation typically simplify the scene lighting into an environment map w
Externí odkaz:
http://arxiv.org/abs/2208.09480
Autor:
Mahmood, Rafid, Lucas, James, Acuna, David, Li, Daiqing, Philion, Jonah, Alvarez, Jose M., Yu, Zhiding, Fidler, Sanja, Law, Marc T.
Given a small training data set and a learning algorithm, how much more data is necessary to reach a target validation or test performance? This question is of critical importance in applications such as autonomous driving or medical imaging where co
Externí odkaz:
http://arxiv.org/abs/2207.01725
Publikováno v:
Advances in Neural Information Processing Systems, Volume 34, pages 8984-8997, year 2021
Absence of large-scale labeled data in the practitioner's target domain can be a bottleneck to applying machine learning algorithms in practice. Transfer learning is a popular strategy for leveraging additional data to improve the downstream performa
Externí odkaz:
http://arxiv.org/abs/2206.09386
The dominant line of work in domain adaptation has focused on learning invariant representations using domain-adversarial training. In this paper, we interpret this approach from a game theoretical perspective. Defining optimal solutions in domain-ad
Externí odkaz:
http://arxiv.org/abs/2202.05352