Related papers: Towards Robust 3D Pose Transfer with Adversarial L…
Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for both 2D and 3D computer vision. Nevertheless, existing MAE-based methods still have certain drawbacks. Firstly, the functional decoupling…
Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…
Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning…
Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these…
In this work we integrate ideas from surface-based modeling with neural synthesis: we propose a combination of surface-based pose estimation and deep generative models that allows us to perform accurate pose transfer, i.e. synthesize a new…
We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photorealistic images of full-body humans with consistent appearances under different view-angles and body-poses. To tackle the representational and…
In this paper, we investigate the adversarial robustness of vision transformers that are equipped with BERT pretraining (e.g., BEiT, MAE). A surprising observation is that MAE has significantly worse adversarial robustness than other BERT…
Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prove difficult or time-intensive to scale up to efficacy for…
This paper revisits camera pose estimation through the lens of self-supervised pretraining, focusing on inverse-dynamics pretraining as a scalable alternative to the current trend of fully supervised training with 3D annotations.…
Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by…
Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention…
End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data. This paper proposes a novel data augmentation…
Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees…
We propose a novel end-to-end semi-supervised adversarial framework to generate photorealistic face images of new identities with wide ranges of expressions, poses, and illuminations conditioned by a 3D morphable model. Previous adversarial…
Learning to represent three dimensional (3D) human pose given a two dimensional (2D) image of a person, is a challenging problem. In order to make the problem less ambiguous it has become common practice to estimate 3D pose in the camera…
Adversarial examples have attracted widespread attention in security-critical applications because of their transferability across different models. Although many methods have been proposed to boost adversarial transferability, a gap still…
Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained…
Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increased method complexity. We present the Rotary Masked…
3D human pose and shape estimation (a.k.a. "human mesh recovery") has achieved substantial progress. Researchers mainly focus on the development of novel algorithms, while less attention has been paid to other critical factors involved.…
With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data…