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

Part Correspondences and Temporal Consistency for Self-Supervised 3D Reconstruction-Shalini De MelloПодробнее

STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural RenderingПодробнее

What do Single-view 3D Reconstruction Network Learn?Подробнее

Deep Single View 3D Object Reconstruction with Visual Hull EmbeddingПодробнее

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head AvatarsПодробнее

Three Ways to Improve Semantic Segmentation with Self Supervised Depth Estimation CVPR21Подробнее

Model-based 3D Hand Reconstruction via Self-Supervised Learning, CVPR2021Подробнее

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

[CVPR 2021] Self-supervised Augmentation Consistency for Adapting Semantic SegmentationПодробнее

[CVPR 2023] Self-Supervised Super-Plane for Neural 3D ReconstructionПодробнее

Steering Self-Supervised Feature Learning Beyond Local Pixel StatisticsПодробнее

Single-View 3D Mesh Reconstruction and GenerationПодробнее

[MERL Seminar Series Spring 2022] Self-Supervised Scene Representation LearningПодробнее

Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical ImПодробнее

SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans (CVPR)Подробнее

Front2Back: Single View 3D Shape Reconstruction via Front to Back PredictionПодробнее

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View ConsistencyПодробнее

Semantic consistency v0 - 512x512 (using VGG loss only)Подробнее

Self-supervised Learning of Interpretable Keypoints from Unlabelled VideosПодробнее