Related papers: Multi-hypotheses Conditioned Point Cloud Diffusion…

Recovering a 3D human mesh from a single RGB image is a challenging task due to depth ambiguity and self-occlusion, resulting in a high degree of uncertainty. Meanwhile, diffusion models have recently seen much success in generating…

Recent advances in 3D human shape reconstruction from single images have shown impressive results, leveraging on deep networks that model the so-called implicit function to learn the occupancy status of arbitrarily dense 3D points in space.…

In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the…

This work focuses on the problem of reconstructing a 3D human body mesh from a given 2D image. Despite the inherent ambiguity of the task of human mesh recovery, most existing works have adopted a method of regressing a single output. In…

Reconstructing 3D humans from a single image has been extensively investigated. However, existing approaches often fall short on capturing fine geometry and appearance details, hallucinating occluded parts with plausible details, and…

We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering…

Monocular 3D human pose and shape estimation is an inherently ill-posed problem due to depth ambiguities, occlusions, and truncations. Recent probabilistic approaches learn a distribution over plausible 3D human meshes by maximizing the…

3D building generation with low data acquisition costs, such as single image-to-3D, becomes increasingly important. However, most of the existing single image-to-3D building creation works are restricted to those images with specific…

We propose a scalable neural network framework to reconstruct the 3D mesh of a human body from multi-view images, in the subspace of the SMPL model. Use of multi-view images can significantly reduce the projection ambiguity of the problem,…

Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task, particularly with real-world data. Current state-of-the-art methods develop Transformer-based implicit field learning, necessitating an…

Millimeter-wave (mmWave) radar offers robust sensing capabilities in diverse environments, making it a highly promising solution for human body reconstruction due to its privacy-friendly and non-intrusive nature. However, the significant…

We present PersonaCraft, a framework for controllable and occlusion-robust full-body personalized image synthesis of multiple individuals in complex scenes. Current methods struggle with occlusion-heavy scenarios and complete body…

Inferring 3D structures from sparse, unposed observations is challenging due to its unconstrained nature. Recent methods propose to predict implicit representations directly from unposed inputs in a data-driven manner, achieving promising…

Creating high-quality 3D models of clothed humans from single images for real-world applications is crucial. Despite recent advancements, accurately reconstructing humans in complex poses or with loose clothing from in-the-wild images,…

Most existing human rendering methods require every part of the human to be fully visible throughout the input video. However, this assumption does not hold in real-life settings where obstructions are common, resulting in only partial…

Humans can infer the missing parts of an occluded object by leveraging prior knowledge and visible cues. However, enabling deep learning models to accurately predict such occluded regions remains a challenging task. De-occlusion addresses…

Latent diffusion models (LDMs) have demonstrated remarkable generative capabilities across various low-level vision tasks. However, their potential for point cloud completion remains underexplored due to the unstructured and irregular…

Pose-guided person image synthesis task requires re-rendering a reference image, which should have a photorealistic appearance and flawless pose transfer. Since person images are highly structured, existing approaches require dense…

The three-dimensional reconstruction of scenes from multiple views has made impressive strides in recent years, chiefly by methods correlating isolated feature points, intensities, or curvilinear structure. In the general setting, i.e.,…

Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image. While diffusion-based reconstructors achieve high accuracy, they typically require many denoising iterations,…