# Masked Depth Modeling for Spatial Perception

arXiv: https://arxiv.org/abs/2601.17895 · HTML: https://mlsanity.com/paper/2601.17895/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details](https://mlsanity.com/paper/2507.02546/) (2025)
- [DIODE: A Dense Indoor and Outdoor DEpth Dataset](https://mlsanity.com/paper/1908.00463/) (2019)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception](https://mlsanity.com/paper/2306.06362/) (2023)
- [ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation](https://mlsanity.com/paper/1910.02550/) (2019)
- [SpatialTrackerV2: 3D Point Tracking Made Easy](https://mlsanity.com/paper/2507.12462/) (2025)
- [Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation](https://mlsanity.com/paper/2412.14015/) (2024)
- [Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects](https://mlsanity.com/paper/2208.03792/) (2022)
- [Open Challenges in Deep Stereo: the Booster Dataset](https://mlsanity.com/paper/2206.04671/) (2022)
- [Depth Anything with Any Prior](https://mlsanity.com/paper/2505.10565/) (2025)
- [OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration](https://mlsanity.com/paper/2411.19278/) (2024)
- [Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression](https://mlsanity.com/paper/2205.04565/) (2022)
- [D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation](https://mlsanity.com/paper/2409.14365/) (2024)

## Built on by (most cited first, 28 of 28)

- [A Pragmatic VLA Foundation Model](https://mlsanity.com/paper/2601.18692/) (2026)
- [From Foundation to Application: Improving VLA Models in Practice](https://mlsanity.com/paper/2607.06403/) (2026)
- [Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model](https://mlsanity.com/paper/2605.14950/) (2026)
- [WildDet3D: Scaling Promptable 3D Detection in the Wild](https://mlsanity.com/paper/2604.08626/) (2026)
- [MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources](https://mlsanity.com/paper/2601.22054/) (2026)
- [Vision as Unified Multimodal Generation](https://mlsanity.com/paper/2607.06560/) (2026)
- [AoE: Always-on Egocentric Human Video Collection for Embodied AI](https://mlsanity.com/paper/2602.23893/) (2026)
- [Towards Consistent Video Geometry Estimation](https://mlsanity.com/paper/2605.30060/) (2026)
- [3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance](https://mlsanity.com/paper/2606.31329/) (2026)
- [EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control](https://mlsanity.com/paper/2605.21862/) (2026)
- [Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling](https://mlsanity.com/paper/2608.30821/) (2026)
- [GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models](https://mlsanity.com/paper/2606.03240/) (2026)
- [SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving](https://mlsanity.com/paper/2606.16960/) (2026)
- [PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation](https://mlsanity.com/paper/2608.16984/) (2026)
- [Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction](https://mlsanity.com/paper/2605.26230/) (2026)
- [SpatialBench: Is Your Spatial Foundation Model an All-Round Player?](https://mlsanity.com/paper/2605.27367/) (2026)
- [AFUN: Towards an Affordance Foundation Model for Functionality Understanding](https://mlsanity.com/paper/2606.02551/) (2026)
- [DarkVGGT: Seeing Through Darkness Using Thermal Geometry](https://mlsanity.com/paper/2606.11326/) (2026)
- [Streaming Neural Speech Codecs through Time-Invariant Representations](https://mlsanity.com/paper/2607.05250/) (2026)
- [Enhancing In-context Panoramic Generation via Geometric-aware Pretraining](https://mlsanity.com/paper/2607.08765/) (2026)
- [V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models](https://mlsanity.com/paper/2608.25308/) (2026)
- [DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2609.31103/) (2026)
- [FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution](https://mlsanity.com/paper/2609.32323/) (2026)
- [E-WAVE: Event-based Continuous Optical Flow via Warping-Aligned Visual Encoding](https://mlsanity.com/paper/2609.34346/) (2026)
- [F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement](https://mlsanity.com/paper/2609.35575/) (2026)
- [OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection](https://mlsanity.com/paper/2610.03015/) (2026)
- [EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder](https://mlsanity.com/paper/2610.04554/) (2026)
- [ASM-6D: Fast Certified Pose-Shape Inference with Complete Correspondence Flow Maps](https://mlsanity.com/paper/2610.15287/) (2026)

## Abstract (arXiv)

Spatial visual perception is a fundamental requirement in physical-world applications like autonomous driving and robotic manipulation, driven by the need to interact with 3D environments. Capturing pixel-aligned metric depth using RGB-D cameras would be the most viable way, yet it usually faces obstacles posed by hardware limitations and challenging imaging conditions, especially in the presence of specular or texture-less surfaces. In this work, we argue that the inaccuracies from depth sensors can be viewed as "masked" signals that inherently reflect underlying geometric ambiguities. Building on this motivation, we present LingBot-Depth, a depth completion model which leverages visual context to refine depth maps through masked depth modeling and incorporates an automated data curation pipeline for scalable training. It is encouraging to see that our model outperforms top-tier RGB-D cameras in terms of both depth precision and pixel coverage. Experimental results on a range of downstream tasks further suggest that LingBot-Depth offers an aligned latent representation across RGB and depth modalities. We release the code, checkpoint, and 3M RGB-depth pairs (including 2M real data and 1M simulated data) to the community of spatial perception.