Multi-View Depth Estimation

Overview

Multi-view depth estimation uses images from different viewpoints to infer scene depth, resolve scale ambiguity, and build consistent 3D geometry for applications such as mapping, robotics, and autonomous driving. Classical multi-view stereo methods use camera calibration, feature matching, plane-sweep cost volumes, and geometric optimization, while newer transformers use camera-aware features and cross-view attention to combine evidence across images. Many systems also incorporate monocular depth foundation-model priors, sparse LiDAR anchors, temporal video cues, or self-supervised consistency to handle sparse views, occlusions, and changing scenes. A central challenge is balancing accurate, globally consistent geometry with efficiency and generalization across camera types, domains, and dynamic environments.

Latest papers

CardsList

27 papers3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

  1. Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive Gating

    Nov 16, 2026Arda Cinar Demirtas, Pablo Varela Bernal, Marc Pollefeys +1Multi-View Depth EstimationEvent-Based Vision

  2. Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments

    Nov 3, 2026Zhipeng Zhong, Matthew Coombes, Cunjia Liu3D Reconstruction3D Reconstruction Benchmarks

  3. Rethinking Asymmetry in Self-Supervised 3D Geometry Learning

    Oct 30, 2026Gyeongjin Kang, Freeman Cheng, Botao Ye +33D Representation LearningMulti-View 3D Reconstruction

  4. Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry

    Oct 14, 2026Soumick Sarker, Mengmi Zhang3D ReconstructionStreaming 3D Reconstruction

  5. WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention

    Oct 12, 2026Mijeong Kim, Kyujin Lim, Bohyung HanRotary Positional EmbeddingsMulti-View 3D Reconstruction

  6. DepthWorld: 3D World Model for Robot Manipulation

    Oct 6, 2026Jai Bardhan, Josef Sivic, Vladimir PetrikMulti-View Depth EstimationWorld Models for Robotics

  7. Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models

    Oct 1, 2026Xinhao Xiang, Weiyang Li, Zhijie Zheng +2Multi-View Depth Estimation4D Reconstruction

  8. Revisiting Multi-View Stereo: A Sequence-to-Sequence Formulation

    Sep 21, 2026Aoxiang Fan, Corentin Dumery, Nicolas Talabot +1Multi-View Depth Estimation3D ViTs

  9. ZipMVS: Multi-View Stereo with Compressed Cost Volumes

    Aug 28, 2026Guanglin Jin, Hongshan Yu, Javier Civera +1Multi-View 3D ReconstructionMulti-View Depth Estimation

  10. M2Depth: Unifying Monocular Depth Foundation Priors with Multi-View Stereo

    Aug 21, 2026Byeonggwon Lee, Sanggi Lee, Siwoo Lee +2Multi-View Depth EstimationMulti-View 3D Reconstruction

  11. LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation

    Aug 4, 2026Tianbao Zhang, Zeyu Liu, Shuyu Wu +4Multi-View Depth EstimationDepth Estimation

  12. X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

    Jul 14, 2026Heng Zhou, Shuhong Liu, Yonghao He +6Multi-View Depth EstimationMetric Depth Estimation

  13. Wat3R: Underwater 3D Geometry Learning without Annotations

    Jul 9, 2026Jiangwei Ren, Xingyu Jiang, Zijie Song +4Multi-View Depth EstimationUnderwater Imaging

  14. OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras

    Jul 3, 2026Chaesong Park, Jihyeon Hwang, Muyeol Sung +1Multi-View Depth EstimationMulti-View Feature Fusion

  15. SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving

    Jun 15, 2026Shuai Yuan, Runxi Tang, Yuzhou Ji +8Multi-View Depth EstimationMulti-View Consistency

  16. ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereo

    May 31, 2026Guo Pu, Yixuan Han, Zhouhui LianMulti-View Depth Estimation3D Reconstruction

  17. PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement

    Apr 24, 2026David Recasens, Robert Maier, Aljaz Bozic +4Multi-View Depth EstimationDepth Estimation

  18. Self-Improving 4D Perception via Self-Distillation

    Apr 9, 2026Nan Huang, Pengcheng Yu, Weijia Zeng +4Video Depth Estimation4D Reconstruction

  19. Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles

    Apr 3, 2026Weimin Liu, Jiyuan Qiu, Wenjun Wang +1Self-Supervised Monocular Depth EstimationDepth Estimation

  20. Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization

    Mar 16, 2026Lehuai Xu, Weiming Zhang, Yang Li +2Panoramic Depth EstimationStereo Matching

  21. Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos

    Mar 12, 2026Shuo Sun, Unal Artan, Malcolm Mielle +2Multi-View Depth EstimationMulti-View 3D Reconstruction

  22. LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving

    Mar 4, 2026Qihao Sun, Jiarun Liu, Ziqian Ni +5Multi-View Depth EstimationDepth Estimation