No article text was recorded for this version.
2D-3D modality gap
Version 1 of 177 papers82 conceptsfrozen 2026-10-04
Papers in this version
- Blog: CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
- Blog: Explicitly Guided Information Interaction Network for Cross-Modal Point Cloud Completion
- Blog: EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization
- Blog: AutoInst: Automatic Instance-Based Segmentation of LiDAR 3D Scans
- Blog: Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
- Blog: VPN: Learning Video-Pose Embedding for Activities of Daily Living
- Blog: Robust Point Cloud Registration Framework Based on Deep Graph Matching
- Blog: Multi-Task Multi-Sensor Fusion for 3D Object Detection
- Blog: Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
- Blog: HAECcity: Open-Vocabulary Scene Understanding of City-Scale Point Clouds with Superpoint Graph Clustering
- Blog: A Survey for Foundation Models in Autonomous Driving
- Blog: Exploiting point-language models with dual-prompts for 3D anomaly detection
- Blog: CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis
- Blog: End-to-End 2D-3D Registration Between Image and LiDAR Point Cloud for Vehicle Localization
- Blog: Multi-View Representation is What You Need for Point-Cloud Pre-Training
- Blog: Frozen CLIP Model is An Efficient Point Cloud Backbone
- Blog: Adaptive Agent Selection and Interaction Network for Image-to-point cloud Registration
- Blog: Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion
- Blog: Deformable Feature Aggregation for Dynamic Multi-modal 3D Object Detection
- Blog: DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-directional Structure Alignment
- Blog: Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
- Blog: 2D3D-DescNet: Jointly Learning 2D and 3D Local Feature Descriptors for Cross-Dimensional Matching
- Blog: DVG-Diffusion: Dual-View-Guided Diffusion Model for CT Reconstruction From X-Rays
- Blog: Mix3D: Out-of-Context Data Augmentation for 3D Scenes
- Blog: Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval
- Blog: Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
- Blog: Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network
- Blog: Joint 2D-3D-Semantic Data for Indoor Scene Understanding
- Blog: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
- Blog: Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
- Blog: SaliencyI2PLoc: saliency-guided image-point cloud localization using contrastive learning
- Blog: BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
- Blog: Projective Urban Texturing
- Blog: 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
- Blog: Stereo Object Matching Network
- Blog: FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
- Blog: Cross-Modal 3D Representation with Multi-View Images and Point Clouds
- Blog: ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation
- Blog: MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding
- Blog: Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching
- Blog: OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
- Blog: Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem
- Blog: Predator: Registration of 3D Point Clouds With Low Overlap
- Blog: 3D Pick & Mix: Object Part Blending in Joint Shape and Image Manifolds
- Blog: LUOJIA Explorer PMS: Panoramic Odometry and Mapping with Structural Information
- Blog: Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration Using Topology Relationship
- Blog: RayI2P: Learning Rays for Image-to-Point Cloud Registration
- Blog: FloNa: Floor Plan Guided Embodied Visual Navigation
- Blog: 2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
- Blog: GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning
- Blog: FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated Depth
- Blog: Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
- Blog: LiteFusion: Taming 3D Object Detectors from Vision-Based to Multi-Modal with Minimal Adaptation
- Blog: Pulp Motion: Framing-aware multimodal camera and human motion generation
- Blog: Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps
- Blog: CoFiI2P: Coarse-to-Fine Correspondences-Based Image to Point Cloud Registration
- Blog: Nonrigid Object Contact Estimation With Regional Unwrapping Transformer
- Blog: Regularizing Long Short Term Memory with 3D Human-Skeleton Sequences for Action Recognition
- Blog: RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
- Blog: Vehicle Trajectory Estimation Method by Drive Recorder Images and Point Cloud of Surrounding Environment
Showing 60 of 77 papers.
History & citation
Current · Permanent link
- This direction split from Cross-Modal Knowledge Transfer for 3D Point Clouds (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_2d_3d_modality_gap_9f27fa30,
title = {2D-3D modality gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/2d-3d-modality-gap/rdr_9f27fa30713d4c6eafd0338950f09a3f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_2d_3d_modality_gap_9f27fa30_v1,
title = {2D-3D modality gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/2d-3d-modality-gap/rdr_9f27fa30713d4c6eafd0338950f09a3f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}