paper-with-me

3D Human Reconstruction

10개 벤치마크 · 논문 121편 · 이 태스크의 논문 보기 →

Benchmarks

4D-DRESS

결과 22개

CustomHumans

결과 8개

AGORA

결과 5개

CAPE

결과 4개

BEHAVE

결과 3개

EHF

결과 3개

Surreal

결과 2개

Dynamic FAUST

결과 1개

Most implemented

Papers

DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion

2026-08-21 · Jiakun Li, Li Fang, Hao Zhu, Fei Hu 외 arxiv

Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstr…

Zero-shot Generalization3D Human Reconstruction3D Reconstruction

GraphiContact: Pose-aware Human-Scene Robust Contact Perception for Interactive Systems

2026-03-19 · Xiaojian Lin, Yaomin Shen, Junyuan Ma, Yujie Sun 외 arxiv

Monocular vertex-level human-scene contact prediction is a fundamental capability for interactive systems such as assistive monitoring, embodied AI, and rehabilitation analysis. In this work, we study this task jointly w…

3D Human Reconstruction

CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image

2026-03-18 · Yizheng Song, Yiyu Zhuang, Qipeng Xu, Haixiang Wang 외 arxiv

Single-view 3D human reconstruction has garnered significant attention in recent years. Despite numerous advancements, prior research has concentrated on reconstructing 3D models from clear, close-up images of individual…

3D Human Reconstruction

OAHuman: Occlusion-Aware 3D Human Reconstruction from Monocular Images

2026-03-15 · Yuanwang Yang, Hongliang Liu, Muxin Zhang, Nan Ma 외 arxiv

Monocular 3D human reconstruction in real-world scenarios remains highly challenging due to frequent occlusions from surrounding objects, people, or image truncation. Such occlusions lead to missing geometry and unreliab…

3D Human Reconstruction

Biomechanically Accurate Gait Analysis: A 3d Human Reconstruction Framework for Markerless Estimation of Gait Parameters

2026-03-03 · Akila Pemasiri, Ethan Goan, Glen Lichtwark, Robert Schuster 외 arxiv

This paper presents a biomechanically interpretable framework for gait analysis using 3D human reconstruction from video data. Unlike conventional keypoint based approaches, the proposed method extracts biomechanically m…

3D Human Reconstruction

Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild

2026-03-03 · Seunguk Do, Minwoo Huh, Joonghyuk Shin, Jaesik Park arxiv

Single-view 3D human reconstruction has achieved remarkable progress through the adoption of multi-view diffusion models, yet the recovered 3D humans often exhibit unnatural poses. This phenomenon becomes pronounced when…

3D Human Reconstruction

전체 121편 보기 →