A conditional deep generative model of people in natural images

A conditional deep generative model of people in natural images

We propose a deep generative model of humans in natural images which keeps 2D pose separated from other latent factors of variation, such as background scene and clothing. In contrast to methods that learn generative models of low-dimensional representations, e.g., segmentation masks and 2D skeleton...

Descripció completa

Dades bibliogràfiques
Autors principals:	De Bem, R, Ghosh, A, Boukhayma, A, Ajanthan, T, Siddharth, N, Torr, P
Format:	Conference item
Publicat:	IEEE 2019

Ítems similars

DGPose: Deep Generative Models for Human Body Analysis
per: de Bem, R, et al.
Publicat: (2020)

A semi-supervised deep generative model for human body analysis
per: De Bem, R, et al.
Publicat: (2019)

3D hand shape and pose from images in the wild
per: Boukhayma, A, et al.
Publicat: (2020)

Looking deep at people: towards understanding and generating humans in images with deep learning
per: de Bem, RA
Publicat: (2018)

Cross-modal deep face normals with deactivable skip connections
per: Abrevaya, VF, et al.
Publicat: (2020)

Variational mixture-of-experts autoencoders for multi-modal deep generative models
per: Shi, Y, et al.
Publicat: (2019)

SNIP: single-shot network pruning based on connection sensitivity
per: Lee, N, et al.
Publicat: (2019)

Learning disentangled representations with semi-supervised deep generative models
per: Siddharth, N, et al.
Publicat: (2018)

Riemannian walk for incremental learning: Understanding forgetting and intransigence
per: Chaudhry, A, et al.
Publicat: (2018)

Deep fully-connected part-based models for human pose estimation
per: De Bem, R, et al.
Publicat: (2018)

Proximal mean-field for neural network quantization
per: Ajanthan, T, et al.
Publicat: (2020)

A signal propagation perspective for pruning neural networks at initialization
per: Lee, N, et al.
Publicat: (2019)

Understanding the effects of data parallelism and sparsity on neural network training
per: Lee, N, et al.
Publicat: (2020)

Data parallelism in training sparse neural networks
per: Lee, N, et al.
Publicat: (2020)

Similarity learning for dense label transfer
per: Najafi, M, et al.
Publicat: (2018)

Efficient linear programming for dense CRFs
per: Mudigonda, P, et al.
Publicat: (2017)

Comparison of Two in Pixel Source Follower Schemes for Deep Subelectron Noise CMOS Image Sensors
per: Assim Boukhayma, et al.
Publicat: (2022-01-01)

Mirror Descent view for Neural Network quantization
per: Ajanthan, T, et al.
Publicat: (2021)

Higher Order Conditional Random Fields in Deep Neural Networks
per: Arnab, A, et al.
Publicat: (2016)

Controllable text-to-image generation
per: Li, B, et al.
Publicat: (2019)

Controllable text-to-image generation
per: Li, B, et al.
Publicat: (2019)

Noise Reduction Techniques and Scaling Effects towards Photon Counting CMOS Image Sensors
per: Assim Boukhayma, et al.
Publicat: (2016-04-01)

Deep generative models for natural language processing
per: Miao, Y
Publicat: (2017)

Deep generative modeling of annotated bacterial biofilm images
per: Angelina A. Holicheva, et al.
Publicat: (2025-01-01)

Learning to adapt for stereo
per: Tonioni, A, et al.
Publicat: (2020)

Which model generated this image? A model-agnostic approach for origin attribution
per: Liu, F, et al.
Publicat: (2024)

Continual learning with tiny episodic memories
per: Chaudhry, A, et al.
Publicat: (2019)

Memory-driven text-to-image generation
per: Li, B, et al.
Publicat: (2022)

Efficient relaxations for dense CRFs with sparse higher-order potentials
per: Joy, T, et al.
Publicat: (2019)

Model-agnostic origin attribution of generated images with few-shot examples
per: Liu, F, et al.
Publicat: (2024)

Local and blobal GANs with semantic-aware upsampling for image generation
per: Tang, H, et al.
Publicat: (2022)

XingGAN for person image generation
per: Tang, H, et al.
Publicat: (2020)

Bipartite graph reasoning GANs for person image generation
per: Tang, H, et al.
Publicat: (2021)

Deep generative modeling for image synthesis and manipulation
per: Yu, Yingchen
Publicat: (2024)

Image restoration and representation with deep generative models
per: Wang, Yufei
Publicat: (2025)

SCGG: A deep structure-conditioned graph generative model.
per: Faezeh Faez, et al.
Publicat: (2022-01-01)

SCGG: A deep structure-conditioned graph generative model
per: Faezeh Faez, et al.
Publicat: (2022-01-01)

Multi-agent diverse generative adversarial networks
per: Ghosh, A, et al.
Publicat: (2018)

Latent guard: a safety framework for text-to-image generation
per: Liu, R, et al.
Publicat: (2024)

Conditional random fields meet deep neural networks for semantic segmentation: combining probabilistic graphical models with deep learning for structured prediction
per: Arnab, A, et al.
Publicat: (2018)