paper-with-me

Papers

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

2020-03-13 · ECCV 2020 8 · Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz

We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D supervision, manually annotated keypoints, multi-view images of an object or a prior 3D template. The key insight of our work is that objects can be represented as a collection of deformable parts, and each part is semantically coherent across different instances of the same category (e.g., wings on birds and wheels on cars). Therefore, by leveraging self-supervisedly learned part segmentation of a large collection of category-specific images, we can effectively enforce semantic consistency between the reconstructed meshes and the original images. This significantly reduces ambiguities during joint prediction of shape and camera pose of an object, along with texture. To the best of our knowledge, we are the first to try and solve the single-view reconstruction problem without a category-specific template mesh or semantic keypoints. Thus our model can easily generalize to various object categories without such labels, e.g., horses, penguins, etc. Through a variety of experiments on several categories of deformable and rigid objects, we demonstrate that our unsupervised method performs comparably if not better than existing category-specific reconstruction methods learned with supervision.

📄 PDF Abstract BibTeX arXiv:2003.06473

Code (1)

nvlabs/umr pytorch

Tasks

3D ReconstructionObjectSingle-View 3D Reconstruction

Similar Papers 제목 키워드 기반

SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields

2022-12-05 · ICCV 2023 1 · Anh-Quan Cao, Raoul de Charette

3D reconstruction from a single 2D image was extensively covered in the literature but relies on depth supervision at training time, which limits its applicability. To relax the dependence to depth we propose SceneRF, a …

3D Reconstruction3D Scene ReconstructionAutonomous DrivingDepth Estimation+4

Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

2025-09-01 · Xiangdong Zhang, Shaofeng Zhang, Junchi Yan arxiv

Point cloud learning, especially in a self-supervised way without manual labels, has gained growing attention in both vision and learning communities due to its potential utility in a wide range of applications. Most exi…

Self-Supervised LearningPoint Clouds

Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning

2022-01-01 · CVPR 2022 1 · Guangrun Wang, Yansong Tang, Liang Lin, Philip H.S. Torr

The resurgence of unsupervised learning can be attributed to the remarkable progress of self-supervised learning, which includes generative (G) and discriminative (D) models. In computer vision, the mainstream self-s…

Image ReconstructionRepresentation LearningSelf-Supervised Learning

Self-Supervised 3D Mesh Reconstruction From Single Images

2021-06-19 · CVPR 2021 1 · Tao Hu, LiWei Wang, Xiaogang Xu, Shu Liu 외

Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation. However, without explicit 3D attribute-level supervision, it is still diffi…

3D ReconstructionAttributeImage GenerationSingle-View 3D Reconstruction

VLRC: Vision-Language Reprojection Consistency as a scalable signal for better feed-forward 3D pretraining

2026-07-02 · Marwane Hariat, David Filliat, Antoine Manzanera arxiv

Feed-forward 3D models are commonly trained using either expensive geometric supervision or self-supervised photometric objectives, both of which provide incomplete learning signals. We introduce Vision-Language Reprojec…

3D Semantic SegmentationScene Understanding3D Reconstruction