Related papers: PeopleSansPeople: A Synthetic Data Generator for H…

A major limitation to advances in fingerprint spoof detection is the lack of publicly available, large-scale fingerprint spoof datasets, a problem which has been compounded by increased concerns surrounding privacy and security of biometric…

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…

We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data. The high cost of collecting and annotating data in the real-world has motivated the use of…

Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of…

Human-centric perception is the core of diverse computer vision tasks and has been a long-standing research focus. However, previous research studied these human-centric tasks individually, whose performance is largely limited to the size…

Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based…

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which…

The availability of large-scale face datasets has been key in the progress of face recognition. However, due to licensing issues or copyright infringement, some datasets are not available anymore (e.g. MS-Celeb-1M). Recent advances in…

Person image synthesis, e.g., pose transfer, is a challenging problem due to large variation and occlusion. Existing methods have difficulties predicting reasonable invisible regions and fail to decouple the shape and style of clothing,…

Training methods to perform robust 3D human pose and shape (HPS) estimation requires diverse training images with accurate ground truth. While BEDLAM demonstrates the potential of traditional procedural graphics to generate such data, the…

Recent text-to-image generative models have exhibited remarkable abilities in generating high-fidelity and photo-realistic images. However, despite the visually impressive results, these models often struggle to preserve plausible human…

We propose an algorithm to generate realistic face images of both real and synthetic identities (people who do not exist) with different facial yaw, shape and resolution.The synthesized images can be used to augment datasets to train CNNs…

In the field of deep learning applied to face recognition, securing large-scale, high-quality datasets is vital for attaining precise and reliable results. However, amassing significant volumes of high-quality real data faces hurdles such…

Despite considerable efforts to enhance the generalization of 3D pose estimators without costly 3D annotations, existing data augmentation methods struggle in real world scenarios with diverse human appearances and complex poses. We propose…

Generative AI now produces photorealistic portraits that circulate widely in social and newslike contexts. Human ability to distinguish real from synthetic faces is time-sensitive because image generators continue to improve while public…

Today's legal restrictions that protect the privacy of biometric data are hampering fingerprint recognition researches. For instance, all high-resolution fingerprint databases ceased to be publicly available. To address this problem, we…

Synthetic data generation is an appealing tool for augmenting and enriching datasets, playing a crucial role in advancing artificial intelligence (AI) and machine learning (ML). Not only does synthetic data help build robust AI/ML datasets…

In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric…

Diverse, accurately labeled 3D human pose data is expensive and studio-bound, while in-the-wild datasets lack known ground truth. We introduce UnrealPose-Gen, an Unreal Engine 5 pipeline built on Movie Render Queue for high-quality offline…

We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model. The proposed PersonLab model tackles both semantic-level reasoning…