Learning 3D object categories by looking around them

Learning 3D object categories by looking around them

Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese...

書誌詳細
主要な著者:	Novotny, D, Larlus, D, Vedaldi, A
フォーマット:	Conference item
言語:	English
出版事項:	IEEE 2017

類似資料

Capturing the geometry of object categories from video supervision
著者:: Novotny, D, 等
出版事項: (2018)

I have seen enough: Transferring parts across categories
著者:: Novotny, D, 等
出版事項: (2016)

Learning the semantic structure of objects from Web supervision
著者:: Novotny, D, 等
出版事項: (2016)

Unsupervised learning of 3D object categories from videos in the wild
著者:: Henzler, P, 等
出版事項: (2021)

NeuralDiff: Segmenting 3D objects that move in egocentric videos
著者:: Tschernezki, V, 等
出版事項: (2022)

AnchorNet: A weakly supervised network to learn geometry-sensitive features for semantic matching
著者:: Novotny, D, 等
出版事項: (2017)

Self-supervised learning of geometrically stable features through probabilistic introspection
著者:: Novotny, D, 等
出版事項: (2018)

No representation rules them all in category discovery
著者:: Vaze, S, 等
出版事項: (2024)

Catfree3d: category-agnostic 3D object detection with diffusion
著者:: Bian, W, 等
出版事項: (2024)

Semi-convolutional operators for instance segmentation
著者:: Novotny, D, 等
出版事項: (2018)

Discovering relationships between object categories via universal canonical maps
著者:: Neverova, N, 等
出版事項: (2021)

Canonical 3D Deformer Maps: unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
著者:: Novotny, D, 等
出版事項: (2020)

Learning the structure of object categories from incomplete supervision
著者:: Novotny, D
出版事項: (2018)

Neural feature fusion fields: 3D distillation of self-supervised 2D image representations
著者:: Tschernezki, V, 等
出版事項: (2023)

Modelling and unsupervised learning of symmetric deformable object categories
著者:: Thewlis, J, 等
出版事項: (2018)

Common pets in 3D: dynamic new-view synthesis of real-life deformable categories
著者:: Sinha, S, 等
出版事項: (2023)

DensePose 3D: lifting canonical surface maps of articulated objects to the third dimension
著者:: Shapovalov, R, 等
出版事項: (2022)

DOVE: learning deformable 3D objects by watching videos
著者:: Wu, S, 等
出版事項: (2023)

EPIC Fields: marrying 3D geometry and video understanding
著者:: Tschernezki, V, 等
出版事項: (2023)

EPIC Fields: marrying 3D geometry and video understanding
著者:: Tschernezki, V, 等
出版事項: (2024)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
著者:: Wu, S, 等
出版事項: (2021)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
著者:: Wu, S, 等
出版事項: (2020)

On completeness and cocompleteness in and around small categories
著者:: Pavlovic, D
出版事項: (1995)

HoloDiffusion: training a 3D diffusion model using 2D Images
著者:: Karnewar, A, 等
出版事項: (2023)

Hypostases of THEM category in mass media communication
著者:: Chanysheva Zulfira Zakievna
出版事項: (2016-10-01)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild (extended abstract)
著者:: Wu, S, 等
出版事項: (2021)

Learning to discover novel visual categories via deep transfer clustering
著者:: Han, K, 等
出版事項: (2020)

GOEnFusion: gradient origin encodings for 3D forward diffusion models
著者:: Karnewar, A, 等
出版事項: (2023)

Neural fields for co-reconstructing 3D objects from incidental 2D data
著者:: Campbell, D, 等
出版事項: (2024)

Transfer learning for object category detection
著者:: Aytar, Y
出版事項: (2014)

Generalized category discovery
著者:: Vaze, S, 等
出版事項: (2022)

Learners’ Beliefs and Communities Around Them: The Social Pressure to Learn Language
著者:: Munassir Alhamami
出版事項: (2020-01-01)

AutoNovel: automatically discovering and learning novel visual categories
著者:: Han, K, 等
出版事項: (2021)

Automatically discovering and learning new visual categories with ranking statistics
著者:: Han, K, 等
出版事項: (2020)

3D Multi-bodies: fitting sets of plausible 3D human models to ambiguous image data
著者:: Biggs, B, 等
出版事項: (2020)

Lifting 2D object locations to 3D by discounting LiDAR outliers across objects and views
著者:: McCraith, R, 等
出版事項: (2022)

How larvae feel the world around them
著者:: Jimena Berni
出版事項: (2024-03-01)

C3DPO: Canonical 3D pose networks for non-rigid structure from motion
著者:: Novotny, D, 等
出版事項: (2020)

Scene Recognition With Objectness, Attribute, and Category Learning
著者:: Li-Hui Zhao, 等
出版事項: (2024-01-01)

Circling around:looking(s) and empathies
著者:: Keefe, John
出版事項: (2020)