1. SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Jianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu, Wei Jiang, Hujun Bao, Xiaowei Zhou
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view. Addressing this ambiguity requires to aggregate various cues over the entire image, such as body sizes, scene layouts, and inter-person relationships. However, most previous methods adopt a top-down scheme that first performs 2D pose detection and then regresses the 3D pose and scale for each detected person individually, ignoring global contextual cues. In this paper, we propose a novel system that first regresses a set of 2.5D representations of body parts and then reconstructs the 3D absolute poses based on these 2.5D representations with a depth-aware part association algorithm. Such a single-shot bottom-up scheme allows the system to better learn and reason about the inter-person depth relationship, improving both 3D and 2D pose estimation. The experiments demonstrate that the proposed approach achieves the state-of-the-art performance on the CMU Panoptic and MuPoTS-3D datasets and is applicable to in-the-wild videos.
SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
— AK (@ak92501) August 27, 2020
pdf: https://t.co/t3j8UChX2G
abs: https://t.co/He0TLboPbF
project page: https://t.co/xyb9qX2IkV
github: https://t.co/91b43ywVv2 pic.twitter.com/ovYUFM9brA
2. What is being transferred in transfer learning?
Behnam Neyshabur, Hanie Sedghi, Chiyuan Zhang
One desired capability for machines is the ability to transfer their knowledge of one domain to another where data is (usually) scarce. Despite ample adaptation of transfer learning in various deep learning applications, we yet do not understand what enables a successful transfer and which part of the network is responsible for that. In this paper, we provide new tools and analyses to address these fundamental questions. Through a series of analyses on transferring to block-shuffled images, we separate the effect of feature reuse from learning low-level statistics of data and show that some benefit of transfer learning comes from the latter. We present that when training from pre-trained weights, the model stays in the same basin in the loss landscape and different instances of such model are similar in feature space and close in parameter space.
Have you been thinking about “what is being transferred in transfer learning?” and what parts of the network are in charge of that? We have some answers for you! https://t.co/74I8ec1Tix with @bneyshabur and Chiyuan Zhang pic.twitter.com/YcOvNToFtG
— Hanie Sedghi (@HanieSedghi) August 27, 2020
3. NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
Yun-Chun Chen, Chen Gao, Esther Robb, Jia-Bin Huang
Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks. Instead of using hand-designed architectures, we propose to search for neural architectures that capture stronger image priors. Building upon a generic U-Net architecture, our core contribution lies in designing new search spaces for (1) an upsampling cell and (2) a pattern of cross-scale residual connections. We search for an improved network by leveraging an existing neural architecture search algorithm (using reinforcement learning with a recurrent neural network controller). We validate the effectiveness of our method via a wide variety of applications, including image restoration, dehazing, image-to-image translation, and matrix factorization. Extensive experimental results show that our algorithm performs favorably against state-of-the-art learning-free approaches and reaches competitive performance with existing learning-based methods in some cases.
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
— AK (@ak92501) August 27, 2020
pdf: https://t.co/o632NYfCEp
abs: https://t.co/ykz6jSMtrj
project page: https://t.co/BVS8CNjzMA
github: https://t.co/1pZkDP8Huh
colab: https://t.co/1JXhONeQ1l pic.twitter.com/G8Cl6XXGw3
4. Anime-to-Real Clothing: Cosplay Costume Generation via Image-to-Image Translation
Koya Tango, Marie Katsurai, Hayato Maki, Ryosuke Goto
Cosplay has grown from its origins at fan conventions into a billion-dollar global dress phenomenon. To facilitate imagination and reinterpretation from animated images to real garments, this paper presents an automatic costume image generation method based on image-to-image translation. Cosplay items can be significantly diverse in their styles and shapes, and conventional methods cannot be directly applied to the wide variation in clothing images that are the focus of this study. To solve this problem, our method starts by collecting and preprocessing web images to prepare a cleaned, paired dataset of the anime and real domains. Then, we present a novel architecture for generative adversarial networks (GANs) to facilitate high-quality cosplay image generation. Our GAN consists of several effective techniques to fill the gap between the two domains and improve both the global and local consistency of generated images. Experiments demonstrated that, with two types of evaluation metrics, the proposed GAN achieves better performance than existing methods. We also showed that the images generated by the proposed method are more realistic than those generated by the conventional methods. Our codes and pretrained model are available on the web.
Anime-to-Real Clothing: Cosplay Costume Generation via
— AK (@ak92501) August 27, 2020
Image-to-Image Translation
pdf: https://t.co/0M5azjVglX
abs: https://t.co/OcbOxB9amV pic.twitter.com/WdX3aYZJV7