Related papers: PSHuman: Photorealistic Single-image 3D Human Reco…
Pose and body shape editing in a human image has received increasing attention. However, current methods often struggle with dataset biases and deteriorate realism and the person's identity when users make large edits. We propose a one-shot…
This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh…
Generating consistent human images with controllable pose and appearance is essential for applications in virtual try on, image editing, and digital human creation. Current methods often suffer from occlusions, garment style drift, and pose…
Photo-realistic re-rendering of a human from a single image with explicit control over body pose, shape and appearance enables a wide range of applications, such as human appearance transfer, virtual try-on, motion imitation, and novel view…
Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and applicability in diverse real-world scenarios. In this work,…
The generation of 3D clothed humans has attracted increasing attention in recent years. However, existing work cannot generate layered high-quality 3D humans with consistent body structures. As a result, these methods are unable to…
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…
Reconstructing textured 3D human models from a single image is fundamental for AR/VR and digital human applications. However, existing methods mostly focus on single individuals and thus fail in multi-human scenes, where naive composition…
3D human mesh recovery from monocular RGB images aims to estimate anatomically plausible 3D human models for downstream applications, but remains challenging under partial or severe occlusions. Regression-based methods are efficient yet…
Multi-view hand mesh reconstruction is a critical task for applications in virtual reality and human-computer interaction, but it remains a formidable challenge. Although existing multi-view hand reconstruction methods achieve remarkable…
Recent methods for dynamic human reconstruction have attained promising reconstruction results. Most of these methods rely only on RGB color supervision without considering explicit geometric constraints. This leads to existing human…
Super-resolution algorithms often struggle with images from surveillance environments due to adverse conditions such as unknown degradation, variations in pose, irregular illumination, and occlusions. However, acquiring multiple images,…
Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods often suffer from slow inference, produce only coarse body poses, and exhibit…
DreamFusion established a new paradigm for unsupervised 3D reconstruction from virtual views by combining advances in generative models and differentiable rendering. However, the underlying multi-view rendering, along with supervision from…
Reconstructing posed 3D human models from monocular images has important applications in the sports industry, including performance tracking, injury prevention and virtual training. In this work, we combine 3D human pose and shape…
In this paper we predict a full 3D avatar of a person from a single image. We infer texture and geometry in the UV-space of the SMPL model using an image-to-image translation method. Given partial texture and segmentation layout maps…
We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training…
We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision. Recent advances have shifted the interest towards directly regressing parameters of a…
Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an approach to model…
This work presents MExECON, a novel pipeline for 3D reconstruction of clothed human avatars from sparse multi-view RGB images. Building on the single-view method ECON, MExECON extends its capabilities to leverage multiple viewpoints,…