mlsanityData to 14 Oct 2026

FlatLands: Generative Floormap Completion From a Single Egocentric View

arXiv 2603.16016 ↗First posted 16 Mar 2026cs.CV cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and benchmark for single-view bird's-eye view (BEV) floor completion. The dataset contains 270,575 observations from 17,656 real metric indoor scenes drawn from six existing datasets, with aligned observation, visibility, validity, and ground-truth BEV maps, and the benchmark includes both in- and out-of-distribution evaluation protocols. We compare training-free approaches, deterministic models, ensembles, and stochastic generative models. Finally, we instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline. FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 110 of its 173 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

110 of 173 references.

References · 110

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  11. 2022Scalable Diffusion Models with Transformerscited by 6,054
  12. 2022Classifier-Free Diffusion Guidancecited by 5,847
38 more
  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  13. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  14. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  15. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  16. 2018Group Normalizationcited by 1,524
  17. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  18. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  19. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  20. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  21. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  22. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  23. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  24. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  25. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 1,006
  26. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  27. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  28. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  29. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  30. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  31. 2017The Perception-Distortion Tradeoffcited by 587
  32. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  33. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  34. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  35. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  36. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  37. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  38. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422

50 most cited of 110 All 110 (JSON)

Built on by

Not cited yet.