TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Moving Indoor: Unsupervised Video Depth Learning in Challe...

Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments

Junsheng Zhou, Yuwang Wang, Kaihuai Qin, Wen-Jun Zeng

2019-10-20ICCV 2019 10Optical Flow EstimationMonocular Depth Estimation
PaperPDF

Abstract

Recently unsupervised learning of depth from videos has made remarkable progress and the results are comparable to fully supervised methods in outdoor scenes like KITTI. However, there still exist great challenges when directly applying this technology in indoor environments, e.g., large areas of non-texture regions like white wall, more complex ego-motion of handheld camera, transparent glasses and shiny objects. To overcome these problems, we propose a new optical-flow based training paradigm which reduces the difficulty of unsupervised learning by providing a clearer training target and handles the non-texture regions. Our experimental evaluation demonstrates that the result of our method is comparable to fully supervised methods on the NYU Depth V2 benchmark. To the best of our knowledge, this is the first quantitative result of purely unsupervised learning method reported on indoor datasets.

Results

TaskDatasetMetricValueModel
Depth EstimationNYU-Depth V2 self-supervisedAbsolute relative error (AbsRel)0.208Zhou et al
Depth EstimationNYU-Depth V2 self-supervisedRoot mean square error (RMSE)0.712Zhou et al
Depth EstimationNYU-Depth V2 self-superviseddelta_167.4Zhou et al
Depth EstimationNYU-Depth V2 self-superviseddelta_290Zhou et al
Depth EstimationNYU-Depth V2 self-superviseddelta_396.8Zhou et al
3DNYU-Depth V2 self-supervisedAbsolute relative error (AbsRel)0.208Zhou et al
3DNYU-Depth V2 self-supervisedRoot mean square error (RMSE)0.712Zhou et al
3DNYU-Depth V2 self-superviseddelta_167.4Zhou et al
3DNYU-Depth V2 self-superviseddelta_290Zhou et al
3DNYU-Depth V2 self-superviseddelta_396.8Zhou et al

Related Papers

Channel-wise Motion Features for Efficient Motion Segmentation2025-07-17Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16MonoMVSNet: Monocular Priors Guided Multi-View Stereo Network2025-07-15An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan2025-07-11ByDeWay: Boost Your multimodal LLM with DEpth prompting in a Training-Free Way2025-07-11Learning to Track Any Points from Human Motion2025-07-08Beyond Appearance: Geometric Cues for Robust Video Instance Segmentation2025-07-08LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures2025-07-08