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...

Descripció completa

Dades bibliogràfiques
Autors principals:	Novotny, D, Larlus, D, Vedaldi, A
Format:	Conference item
Idioma:	English
Publicat:	IEEE 2017

Ítems similars

Capturing the geometry of object categories from video supervision
per: Novotny, D, et al.
Publicat: (2018)

I have seen enough: Transferring parts across categories
per: Novotny, D, et al.
Publicat: (2016)

Learning the semantic structure of objects from Web supervision
per: Novotny, D, et al.
Publicat: (2016)

Unsupervised learning of 3D object categories from videos in the wild
per: Henzler, P, et al.
Publicat: (2021)

NeuralDiff: Segmenting 3D objects that move in egocentric videos
per: Tschernezki, V, et al.
Publicat: (2022)

AnchorNet: A weakly supervised network to learn geometry-sensitive features for semantic matching
per: Novotny, D, et al.
Publicat: (2017)

Self-supervised learning of geometrically stable features through probabilistic introspection
per: Novotny, D, et al.
Publicat: (2018)

No representation rules them all in category discovery
per: Vaze, S, et al.
Publicat: (2024)

Catfree3d: category-agnostic 3D object detection with diffusion
per: Bian, W, et al.
Publicat: (2024)

Semi-convolutional operators for instance segmentation
per: Novotny, D, et al.
Publicat: (2018)

Discovering relationships between object categories via universal canonical maps
per: Neverova, N, et al.
Publicat: (2021)

Canonical 3D Deformer Maps: unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
per: Novotny, D, et al.
Publicat: (2020)

Learning the structure of object categories from incomplete supervision
per: Novotny, D
Publicat: (2018)

Neural feature fusion fields: 3D distillation of self-supervised 2D image representations
per: Tschernezki, V, et al.
Publicat: (2023)

Modelling and unsupervised learning of symmetric deformable object categories
per: Thewlis, J, et al.
Publicat: (2018)

Common pets in 3D: dynamic new-view synthesis of real-life deformable categories
per: Sinha, S, et al.
Publicat: (2023)

DensePose 3D: lifting canonical surface maps of articulated objects to the third dimension
per: Shapovalov, R, et al.
Publicat: (2022)

DOVE: learning deformable 3D objects by watching videos
per: Wu, S, et al.
Publicat: (2023)

EPIC Fields: marrying 3D geometry and video understanding
per: Tschernezki, V, et al.
Publicat: (2023)

EPIC Fields: marrying 3D geometry and video understanding
per: Tschernezki, V, et al.
Publicat: (2024)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
per: Wu, S, et al.
Publicat: (2021)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild
per: Wu, S, et al.
Publicat: (2020)

On completeness and cocompleteness in and around small categories
per: Pavlovic, D
Publicat: (1995)

HoloDiffusion: training a 3D diffusion model using 2D Images
per: Karnewar, A, et al.
Publicat: (2023)

Hypostases of THEM category in mass media communication
per: Chanysheva Zulfira Zakievna
Publicat: (2016-10-01)

Unsupervised learning of probably symmetric deformable 3D objects from images in the wild (extended abstract)
per: Wu, S, et al.
Publicat: (2021)

Learning to discover novel visual categories via deep transfer clustering
per: Han, K, et al.
Publicat: (2020)

GOEnFusion: gradient origin encodings for 3D forward diffusion models
per: Karnewar, A, et al.
Publicat: (2023)

Neural fields for co-reconstructing 3D objects from incidental 2D data
per: Campbell, D, et al.
Publicat: (2024)

Transfer learning for object category detection
per: Aytar, Y
Publicat: (2014)

Generalized category discovery
per: Vaze, S, et al.
Publicat: (2022)

Learners’ Beliefs and Communities Around Them: The Social Pressure to Learn Language
per: Munassir Alhamami
Publicat: (2020-01-01)

AutoNovel: automatically discovering and learning novel visual categories
per: Han, K, et al.
Publicat: (2021)

Automatically discovering and learning new visual categories with ranking statistics
per: Han, K, et al.
Publicat: (2020)

3D Multi-bodies: fitting sets of plausible 3D human models to ambiguous image data
per: Biggs, B, et al.
Publicat: (2020)

Lifting 2D object locations to 3D by discounting LiDAR outliers across objects and views
per: McCraith, R, et al.
Publicat: (2022)

How larvae feel the world around them
per: Jimena Berni
Publicat: (2024-03-01)

C3DPO: Canonical 3D pose networks for non-rigid structure from motion
per: Novotny, D, et al.
Publicat: (2020)

Scene Recognition With Objectness, Attribute, and Category Learning
per: Li-Hui Zhao, et al.
Publicat: (2024-01-01)

Circling around:looking(s) and empathies
per: Keefe, John
Publicat: (2020)