Related papers: Diversifying Human Pose in Synthetic Data for Aeri…

To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-view ambiguities. Existing solutions typically suffer from poor…

Generating multi-view human images from a single view is a complex and significant challenge. Although recent advancements in multi-view object generation have shown impressive results with diffusion models, novel view synthesis for humans…

Person re-identification (re-ID) concerns the matching of subject images across different camera views in a multi camera surveillance system. One of the major challenges in person re-ID is pose variations across the camera network, which…

In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D…

A unique challenge in creating high-quality animatable and relightable 3D avatars of people is modeling human eyes. The challenge of synthesizing eyes is multifold as it requires 1) appropriate representations for the various components of…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…

Monocular 3D human pose estimation remains a challenging and ill-posed problem, particularly in real-time settings and unconstrained environments. While direct imageto-3D approaches require large annotated datasets and heavy models,…

Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e.g., appearance, pose, foreground, background, local details, global structures, etc. In this paper, we present a novel…

In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach…

The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus…

In visual localization, Absolute Pose Regression (APR) enables real-time 6-DoF camera pose inference from single images, yet critically depends on fine-tuning data quality and coverage. While recent methods leverage 3D Gaussian Splatting…

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to…

Recent progress in stochastic motion prediction, i.e., predicting multiple possible future human motions given a single past pose sequence, has led to producing truly diverse future motions and even providing control over the motion of some…

Synthetic face datasets are increasingly used to overcome the limitations of real-world biometric data, including privacy concerns, demographic imbalance, and high collection costs. However, many existing methods lack fine-grained control…

We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…

Synthetic visual data can provide practically infinite diversity and rich labels, while avoiding ethical issues with privacy and bias. However, for many tasks, current models trained on synthetic data generalize poorly to real data. The…

3D human pose estimation from a monocular image or 2D joints is an ill-posed problem because of depth ambiguity and occluded joints. We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible…

We propose PoseGaussian, a pose-guided Gaussian Splatting framework for high-fidelity human novel view synthesis. Human body pose serves a dual purpose in our design: as a structural prior, it is fused with a color encoder to refine depth…

The "lifting from 2D pose" method has been the dominant approach to 3D Human Pose Estimation (3DHPE) due to the powerful visual analysis ability of 2D pose estimators. Widely known, there exists a depth ambiguity problem when estimating…

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent…