paper-with-me

홈 › Papers

NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets

2020-11-23 · Gyeongsik Moon, Hongsuk Choi, Kyoung Mu Lee

Most 3D human mesh regressors are fully supervised with 3D pseudo-GT human model parameters and weakly supervised with GT 2D/3D joint coordinates as the 3D pseudo-GTs bring great performance gain. The 3D pseudo-GTs are obtained by annotators, systems that iteratively fit 3D human model parameters to GT 2D/3D joint coordinates of training sets in the pre-processing stage of the regressors. The fitted 3D parameters at the last fitting iteration become the 3D pseudo-GTs, used to fully supervise the regressors. Optimization-based annotators, such as SMPLify-X, have been widely used to obtain the 3D pseudo-GTs. However, they often produce wrong 3D pseudo-GTs as they fit the 3D parameters to GT of each sample independently. To overcome the limitation, we present NeuralAnnot, a neural network-based annotator. The main idea of NeuralAnnot is to employ a neural network-based regressor and dedicate it for the annotation. Assuming no 3D pseudo-GTs are available, NeuralAnnot is weakly supervised with GT 2D/3D joint coordinates of training sets. The testing results on the same training sets become 3D pseudo-GTs, used to fully supervise the regressors. We show that 3D pseudo-GTs of NeuralAnnot are highly beneficial to train the regressors. We made our 3D pseudo-GTs publicly available.

📄 PDF Abstract BibTeX arXiv:2011.11232

Code (5)

mks0601/NeuralAnnot_RELEASE 공식 구현 pytorch
facebookresearch/InterHand2.6M pytorch
hongsukchoi/Pose2Mesh_RELEASE pytorch
hongsukchoi/TCMR_RELEASE pytorch
jaehakim97/blurhand_release pytorch

Similar Papers 제목 키워드 기반

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

2023-04-10 · Gyeongsik Moon, Hongsuk Choi, Sanghyuk Chun, Jiyoung Lee 외

Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs). Recently, 3D pseudo-GTs have been widely used to train 3D human mesh estimation networks…

3D Multi-Person Pose Estimation

Skin3D: Detection and Longitudinal Tracking of Pigmented Skin Lesions in 3D Total-Body Textured Meshes

2021-05-02 · Mengliu Zhao, Jeremy Kawahara, Kumar Abhishek, Sajjad Shamanian 외

We present an automated approach to detect and longitudinally track skin lesions on 3D total-body skin surface scans. The acquired 3D mesh of the subject is unwrapped to a 2D texture image, where a trained objected detec…

Lesion Detection

Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN

2026-06-25 · Archer Moore, Mingming Gong, Liam Hodgkinson arxiv

Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit surface representations, often by converting radiance fields …

Reinforcement Learning3D Generation

MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction

2022-11-24 · Kevin Lin, Chung-Ching Lin, Lin Liang, Zicheng Liu 외

Traditional methods of reconstructing 3D human pose and mesh from single images rely on paired image-mesh datasets, which can be difficult and expensive to obtain. Due to this limitation, model scalability is constrained…

3D Human Pose EstimationHand Pose EstimationPose Estimation

Detecting Human-Object Contact in Images

2023-03-06 · CVPR 2023 1 · Yixin Chen, Sai Kumar Dwivedi, Michael J. Black, Dimitrios Tzionas

Humans constantly contact objects to move and perform tasks. Thus, detecting human-object contact is important for building human-centered artificial intelligence. However, there exists no robust method to detect contact…

Object