Monocular Human-Object Reconstruction in the Wild
- URL: http://arxiv.org/abs/2407.20566v2
- Date: Wed, 31 Jul 2024 08:45:19 GMT
- Title: Monocular Human-Object Reconstruction in the Wild
- Authors: Chaofan Huo, Ye Shi, Jingya Wang,
- Abstract summary: We present a 2D-supervised method that learns the 3D human-object spatial relation prior purely from 2D images in the wild.
Our method utilizes a flow-based neural network to learn the prior distribution of the 2D human-object keypoint layout and viewports for each image in the dataset.
- Score: 11.261465071559163
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning the prior knowledge of the 3D human-object spatial relation is crucial for reconstructing human-object interaction from images and understanding how humans interact with objects in 3D space. Previous works learn this prior from datasets collected in controlled environments, but due to the diversity of domains, they struggle to generalize to real-world scenarios. To overcome this limitation, we present a 2D-supervised method that learns the 3D human-object spatial relation prior purely from 2D images in the wild. Our method utilizes a flow-based neural network to learn the prior distribution of the 2D human-object keypoint layout and viewports for each image in the dataset. The effectiveness of the prior learned from 2D images is demonstrated on the human-object reconstruction task by applying the prior to tune the relative pose between the human and the object during the post-optimization stage. To validate and benchmark our method on in-the-wild images, we collect the WildHOI dataset from the YouTube website, which consists of various interactions with 8 objects in real-world scenarios. We conduct the experiments on the indoor BEHAVE dataset and the outdoor WildHOI dataset. The results show that our method achieves almost comparable performance with fully 3D supervised methods on the BEHAVE dataset, even if we have only utilized the 2D layout information, and outperforms previous methods in terms of generality and interaction diversity on in-the-wild images.
Related papers
- StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset [56.71580976007712]
We propose to use the Human-Object Offset between anchors which are densely sampled from the surface of human mesh and object mesh to represent human-object spatial relation.
Based on this representation, we propose Stacked Normalizing Flow (StackFLOW) to infer the posterior distribution of human-object spatial relations from the image.
During the optimization stage, we finetune the human body pose and object 6D pose by maximizing the likelihood of samples.
arXiv Detail & Related papers (2024-07-30T04:57:21Z) - Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns.
A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
arXiv Detail & Related papers (2024-06-17T07:43:53Z) - Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers [28.38686299271394]
We propose a framework for 3D sequence-to-sequence (seq2seq) human pose detection.
Firstly, the spatial module represents the human pose feature by intra-image content, while the frame-image relation module extracts temporal relationships.
Our method is evaluated on Human3.6M, a popular 3D human pose detection dataset.
arXiv Detail & Related papers (2024-01-30T03:00:25Z) - Cross-view and Cross-pose Completion for 3D Human Understanding [22.787947086152315]
We propose a pre-training approach based on self-supervised learning that works on human-centric data using only images.
We pre-train a model for body-centric tasks and one for hand-centric tasks.
With a generic transformer architecture, these models outperform existing self-supervised pre-training methods on a wide set of human-centric downstream tasks.
arXiv Detail & Related papers (2023-11-15T16:51:18Z) - CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from
Unbounded Synthesized Images [10.4286198282079]
We present a method for teaching machines to understand and model the underlying spatial common sense of diverse human-object interactions in 3D.
We show multiple 2D images captured from different viewpoints when humans interact with the same type of objects.
Despite its imperfection of the image quality over real images, we demonstrate that the synthesized images are sufficient to learn the 3D human-object spatial relations.
arXiv Detail & Related papers (2023-08-23T17:59:11Z) - Reconstructing Action-Conditioned Human-Object Interactions Using
Commonsense Knowledge Priors [42.17542596399014]
We present a method for inferring diverse 3D models of human-object interactions from images.
Our method extracts high-level commonsense knowledge from large language models.
We quantitatively evaluate the inferred 3D models on a large human-object interaction dataset.
arXiv Detail & Related papers (2022-09-06T13:32:55Z) - RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objects [68.85305626324694]
Ray-marching in Camera Space (RiCS) is a new method to represent the self-occlusions of foreground objects in 3D into a 2D self-occlusion map.
We show that our representation map not only allows us to enhance the image quality but also to model temporally coherent complex shadow effects.
arXiv Detail & Related papers (2022-05-14T05:35:35Z) - NeuralReshaper: Single-image Human-body Retouching with Deep Neural
Networks [50.40798258968408]
We present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks.
Our approach follows a fit-then-reshape pipeline, which first fits a parametric 3D human model to a source human image.
To deal with the lack-of-data problem that no paired data exist, we introduce a novel self-supervised strategy to train our network.
arXiv Detail & Related papers (2022-03-20T09:02:13Z) - RandomRooms: Unsupervised Pre-training from Synthetic Shapes and
Randomized Layouts for 3D Object Detection [138.2892824662943]
A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets.
Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications.
In this work, we put forward a new method called RandomRooms to accomplish this objective.
arXiv Detail & Related papers (2021-08-17T17:56:12Z) - Learning 3D Human Shape and Pose from Dense Body Parts [117.46290013548533]
We propose a Decompose-and-aggregate Network (DaNet) to learn 3D human shape and pose from dense correspondences of body parts.
Messages from local streams are aggregated to enhance the robust prediction of the rotation-based poses.
Our method is validated on both indoor and real-world datasets including Human3.6M, UP3D, COCO, and 3DPW.
arXiv Detail & Related papers (2019-12-31T15:09:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.