# SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception

arXiv: https://arxiv.org/abs/1812.05642 · HTML: https://mlsanity.com/paper/1812.05642/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

## Built on by (most cited first, 16 of 16)

- [Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2112.13047/) (2021)
- [Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark](https://mlsanity.com/paper/2108.03830/) (2021)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints](https://mlsanity.com/paper/2209.05277/) (2022)
- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction](https://mlsanity.com/paper/2209.06351/) (2022)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR](https://mlsanity.com/paper/2109.09628/) (2021)
- [X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation](https://mlsanity.com/paper/2110.12516/) (2021)
- [GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network](https://mlsanity.com/paper/2112.06782/) (2021)
- [ColDE: A Depth Estimation Framework for Colonoscopy Reconstruction](https://mlsanity.com/paper/2111.10371/) (2021)
- [Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning](https://mlsanity.com/paper/2307.14786/) (2023)
- [Revisiting Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2103.12496/) (2021)
- [Improving Online Performance Prediction for Semantic Segmentation](https://mlsanity.com/paper/2104.05255/) (2021)
- [Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos](https://mlsanity.com/paper/2108.03893/) (2021)
- [Asynchronous Collaborative Localization by Integrating Spatiotemporal Graph Learning with Model-Based Estimation](https://mlsanity.com/paper/2111.03751/) (2021)

## Abstract (arXiv)

Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems. Recent works on unsupervised learning have made considerable progress on perceiving geometry; however, they usually ignore the coherence of objects and perform poorly under scenarios with dark and noisy environments. In contrast, supervised learning algorithms, which are robust, require large labeled geometric dataset. This paper introduces SIGNet, a novel framework that provides robust geometry perception without requiring geometrically informative labels. Specifically, SIGNet integrates semantic information to make depth and flow predictions consistent with objects and robust to low lighting conditions. SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error). In particular, SIGNet improves the dynamic object class performance by 39% in depth prediction and 29% in flow prediction. Our code will be made available at https://github.com/mengyuest/SIGNet