Related papers: UnconFuse: Avatar Reconstruction from Unconstraine…

We present a method to reconstruct time-consistent human body models from monocular videos, focusing on extremely loose clothing or handheld object interactions. Prior work in human reconstruction is either limited to tight clothing with no…

While high fidelity and efficiency are central to the creation of digital head avatars, recent methods relying on 2D or 3D generative models often experience limitations such as shape distortion, expression inaccuracy, and identity…

Recently, implicit neural representation has been widely used to generate animatable human avatars. However, the materials and geometry of those representations are coupled in the neural network and hard to edit, which hinders their…

Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To…

With the increasing demands of applications in virtual reality such as 3D films, virtual Human-Machine Interactions and virtual agents, the analysis of 3D human face analysis is considered to be more and more important as a fundamental step…

We present a novel framework for generating high-quality, animatable 4D avatar from a single image. While recent advances have shown promising results in 4D avatar creation, existing methods either require extensive multiview data or…

While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple image information to reconstruct high-precision 3D models.…

Person re-identification (re-ID) aims to accurately re- trieve a person from a large-scale database of images cap- tured across multiple cameras. Existing works learn deep representations using a large training subset of unique per- sons.…

Current unsupervised 2D-3D human pose estimation (HPE) methods do not work in multi-person scenarios due to perspective ambiguity in monocular images. Therefore, we present one of the first studies investigating the feasibility of…

Much progress has been made in the supervised learning of 3D reconstruction of rigid objects from multi-view images or a video. However, it is more challenging to reconstruct severely deformed objects from a single-view RGB image in an…

Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods are often trained on synthetic data with significant domain…

In this paper, we present a method to reconstruct the world and multiple dynamic humans in 3D from a monocular video input. As a key idea, we represent both the world and multiple humans via the recently emerging 3D Gaussian Splatting…

In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them…

3D human shape and pose estimation from monocular images has been an active area of research in computer vision, having a substantial impact on the development of new applications, from activity recognition to creating virtual avatars.…

In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that takes an image as input and estimates the parameters of the…

Reconstructing 3D objects from a single image remains challenging, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they typically assume…

Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally requires prior knowledge of camera poses for the training…

Reconstructing non-rigid objects with physical plausibility remains a significant challenge. Existing approaches leverage differentiable rendering for per-scene optimization, recovering geometry and dynamics but requiring expensive tuning…

We present UP2You, the first tuning-free solution for reconstructing high-fidelity 3D clothed portraits from extremely unconstrained in-the-wild 2D photos. Unlike previous approaches that require "clean" inputs (e.g., full-body images with…

Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Since the real-world is actually video-based rather than…