mlsanityData to 7 Oct 2026

No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency

arXiv 2602.23559 ↗First posted 27 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present the first study of cross-sensor view synthesis across different modalities. We examine a practical, fundamental, yet widely overlooked problem: getting aligned RGB-X data, where most RGB-X prior work assumes such pairs exist and focuses on modality fusion, but it empirically requires huge engineering effort in calibration. We propose a match-densify-consolidate method. First, we perform RGB-X image matching followed by guided point densification. Using the proposed confidence-aware densification and self-matching filtering, we attain better view synthesis and later consolidate them in 3D Gaussian Splatting (3DGS). Our method uses no 3D priors for X-sensor and only assumes nearly no-cost COLMAP for RGB. We aim to remove the cumbersome calibration for various RGB-X sensors and advance the popularity of cross-sensor learning by a scalable solution that breaks through the bottleneck in large-scale real-world RGB-X data collection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 70 of its 108 references that are in the map. First posted on arXiv 27 Feb 2026.

Builds on

70 of 108 references.

References · 70

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  5. 2024Depth Anything V2cited by 1,385
  6. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  8. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  11. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  12. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
38 more
  1. 2020DISK: Learning local features with policy gradientcited by 310
  2. 2023RoMa: Robust Dense Feature Matchingcited by 296
  3. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  4. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 229
  5. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  6. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  7. 2018LF-Net: Learning Local Features from Imagescited by 151
  8. 2023Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentationcited by 128
  9. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  10. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  11. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 91
  12. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 90
  13. 2024Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentationcited by 71
  14. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  15. 2024OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuningcited by 64
  16. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  17. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  18. 2020Challenge-Aware RGBT Trackingcited by 53
  19. 2021FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentationcited by 45
  20. 2024XoFTR: Cross-modal Feature Matching Transformercited by 45
  21. 2025Infrared and Visible Image Fusion: From Data Compatibility to Task Adaptioncited by 45
  22. 2024MINIMA: Modality Invariant Image Matchingcited by 44
  23. 2024SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Trackingcited by 43
  24. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  25. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  26. 2023Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Taskscited by 41
  27. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  28. 20243D Vision-Language Gaussian Splattingcited by 30
  29. 2024Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalitiescited by 29
  30. 2024StyleBooth: Image Style Editing with Multimodal Instructioncited by 28
  31. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 28
  32. 2022ReDFeat: Recoupling Detection and Description for Multimodal Feature Learningcited by 26
  33. 2021SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Drivingcited by 23
  34. 2024OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterationscited by 23
  35. 2023DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Priorcited by 19
  36. 2022Edge-enhanced Feature Distillation Network for Efficient Super-Resolutioncited by 18
  37. 2022Emergent Visual Sensors for Autonomous Vehiclescited by 18
  38. 2023RGB-X Object Detection via Scene-Specific Fusion Modulescited by 15

50 most cited of 70 All 70 (JSON)

Built on by

Not cited yet.