Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Trulls, Eduard"'
Autor:
Sun, Weiwei, Trulls, Eduard, Tseng, Yang-Che, Sambandam, Sneha, Sharma, Gopal, Tagliasacchi, Andrea, Yi, Kwang Moo
Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods based on point clouds do exist, but they do not perform well when the poin
Externí odkaz:
http://arxiv.org/abs/2312.02362
Semantic 2D maps are commonly used by humans and machines for navigation purposes, whether it's walking or driving. However, these maps have limitations: they lack detail, often contain inaccuracies, and are difficult to create and maintain, especial
Externí odkaz:
http://arxiv.org/abs/2306.05407
Diffusion models generating images conditionally on text, such as Dall-E 2 and Stable Diffusion, have recently made a splash far beyond the computer vision community. Here, we tackle the related problem of generating point clouds, both unconditionall
Externí odkaz:
http://arxiv.org/abs/2303.05916
Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in an image. This greatly limits their applicability, as each instance mu
Externí odkaz:
http://arxiv.org/abs/2206.08460
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other. By doing so, one has the option to query only the points
Externí odkaz:
http://arxiv.org/abs/2103.14167
Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints. We introduce DISK (DIScrete Keypoints), a novel method that overcomes these obstacles by lev
Externí odkaz:
http://arxiv.org/abs/2006.13566
Autor:
Jin, Yuhe, Mishkin, Dmytro, Mishchuk, Anastasiia, Matas, Jiri, Fua, Pascal, Yi, Kwang Moo, Trulls, Eduard
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows easy integr
Externí odkaz:
http://arxiv.org/abs/2003.01587
The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if two patches are not in correspondence, their descriptors will not matc
Externí odkaz:
http://arxiv.org/abs/1908.05547
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution-they operate on individual data points with simple perceptrons and extract conte
Externí odkaz:
http://arxiv.org/abs/1907.02545
We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which performs poorl
Externí odkaz:
http://arxiv.org/abs/1901.07124