JUMPS: Joints Upsampling Method for Pose Sequences
| Autor: | Cedric Thebault, Pierre Hellier, Lucas Mourot, Francois Le Clerc |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Sequence Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Inpainting Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Upsampling Generative model Recurrent neural network 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Representation (mathematics) business Encoder Pose 0105 earth and related environmental sciences |
| Zdroj: | ICPR |
| DOI: | 10.48550/arxiv.2007.01151 |
| Popis: | Human Pose Estimation is a low-level task useful forsurveillance, human action recognition, and scene understandingat large. It also offers promising perspectives for the animationof synthetic characters. For all these applications, and especiallythe latter, estimating the positions of many joints is desirablefor improved performance and realism. To this purpose, wepropose a novel method called JUMPS for increasing the numberof joints in 2D pose estimates and recovering occluded ormissing joints. We believe this is the first attempt to addressthe issue. We build on a deep generative model that combines aGenerative Adversarial Network (GAN) and an encoder. TheGAN learns the distribution of high-resolution human posesequences, the encoder maps the input low-resolution sequencesto its latent space. Inpainting is obtained by computing the latentrepresentation whose decoding by the GAN generator optimallymatches the joints locations at the input. Post-processing a 2Dpose sequence using our method provides a richer representationof the character motion. We show experimentally that thelocalization accuracy of the additional joints is on average onpar with the original pose estimates. Comment: 8 pages, 7 figures, 2 tables |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|