# 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning arXiv: https://arxiv.org/abs/2210.12935 ยท HTML: https://mlsanity.com/paper/2210.12935/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 30 of its 56 references that are in the map. - First posted on arXiv 24 Oct 2022. ## Builds on (most cited first, 30 of 30) - [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020) - [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019) - [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017) - [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019) - [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019) - [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017) - [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020) - [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014) - [3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans](https://mlsanity.com/paper/2002.06289/) (2020) - [Data Distillation: Towards Omni-Supervised Learning](https://mlsanity.com/paper/1712.04440/) (2017) - [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://mlsanity.com/paper/1901.03861/) (2019) - [HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features](https://mlsanity.com/paper/2011.11498/) (2020) - [LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image](https://mlsanity.com/paper/1803.08999/) (2018) - [Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1711.10288/) (2017) - [DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama](https://mlsanity.com/paper/1811.11977/) (2018) - [MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments](https://mlsanity.com/paper/1712.03931/) (2017) - [Corners for Layout: End-to-End Layout Recovery from 360 Images](https://mlsanity.com/paper/1903.08094/) (2019) - [Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density](https://mlsanity.com/paper/2108.10860/) (2021) - [LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering](https://mlsanity.com/paper/2104.00568/) (2021) - [RoomNet: End-to-End Room Layout Estimation](https://mlsanity.com/paper/1703.06241/) (2017) - [Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network](https://mlsanity.com/paper/1903.01804/) (2019) - [Monocular Object and Plane SLAM in Structured Environments](https://mlsanity.com/paper/1809.03415/) (2018) - [Pano2CAD: Room Layout From A Single Panorama Image](https://mlsanity.com/paper/1609.09270/) (2016) - [Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods](https://mlsanity.com/paper/1910.04099/) (2019) - [PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation](https://mlsanity.com/paper/2203.15965/) (2022) - [Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation](https://mlsanity.com/paper/1910.12257/) (2019) - [SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama](https://mlsanity.com/paper/2103.13696/) (2021) - [360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation](https://mlsanity.com/paper/2112.06180/) (2021) - [MVLayoutNet:3D layout reconstruction with multi-view panoramas](https://mlsanity.com/paper/2112.06133/) (2021) - [LayoutMP3D: Layout Annotation of Matterport3D](https://mlsanity.com/paper/2003.13516/) (2020) ## Built on by (most cited first, 4 of 4) - [360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception](https://mlsanity.com/paper/2312.16268/) (2023) - [Self-training Room Layout Estimation via Geometry-aware Ray-casting](https://mlsanity.com/paper/2407.15041/) (2024) - [U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation](https://mlsanity.com/paper/2304.08580/) (2023) - [PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation](https://mlsanity.com/paper/2510.11992/) (2025) ## Abstract (arXiv) We present 360-MLC, a self-training method based on multi-view layout consistency for finetuning monocular room-layout models using unlabeled 360-images only. This can be valuable in practical scenarios where a pre-trained model needs to be adapted to a new data domain without using any ground truth annotations. Our simple yet effective assumption is that multiple layout estimations in the same scene must define a consistent geometry regardless of their camera positions. Based on this idea, we leverage a pre-trained model to project estimated layout boundaries from several camera views into the 3D world coordinate. Then, we re-project them back to the spherical coordinate and build a probability function, from which we sample the pseudo-labels for self-training. To handle unconfident pseudo-labels, we evaluate the variance in the re-projected boundaries as an uncertainty value to weight each pseudo-label in our loss function during training. In addition, since ground truth annotations are not available during training nor in testing, we leverage the entropy information in multiple layout estimations as a quantitative metric to measure the geometry consistency of the scene, allowing us to evaluate any layout estimator for hyper-parameter tuning, including model selection without ground truth annotations. Experimental results show that our solution achieves favorable performance against state-of-the-art methods when self-training from three publicly available source datasets to a unique, newly labeled dataset consisting of multi-view of the same scenes.