No article text was recorded for this version.
cross-modal feature fusion
Version 1 of 11,396 papers1,755 conceptsfrozen 2026-10-04
Papers in this version
- Blog: P4contrast: Contrastive learning with pairs of point-pixel pairs for rgb-d scene understanding
- Blog: PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
- Blog: Viewpoint Selection for Photographing Architectures
- Blog: Voxel- and Bird's-Eye-View-Based Semantic Scene Completion for LiDAR Point Clouds
- Blog: PanoNet3D: Combining Semantic and Geometric Understanding for LiDAR Point Cloud Detection
- Blog: LVIC: Multi-modality segmentation by Lifting Visual Info as Cue
- Blog: Correction: Few Annotated Pixels and Point Cloud Based Weakly Supervised Semantic Segmentation of Driving Scenes
- Blog: ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
- Blog: Cross-Modality Feature Fusion Network for Few-Shot 3D Point Cloud Classification
- Blog: MVX-Net: Multimodal VoxelNet for 3D Object Detection
- Blog: EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video
- Blog: SpatialGeo: Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion
- Blog: A Universal Semantic-Geometric Representation for Robotic Manipulation
- Blog: RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base
- Blog: RISAS: A novel rotation, illumination, scale invariant appearance and shape feature
- Blog: Reasoning in Space via Grounding in the World
- Blog: CPMC-3D-O2P: Semantic segmentation of RGB-D images using CPMC and Second Order Pooling
- Blog: RGB-D datasets using microsoft kinect or similar sensors: a survey
- Blog: Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
- Blog: An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu's Algorithm
- Blog: Graph Neural Networks for 3D Multi-Object Tracking
- Blog: PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition
- Blog: MVX-Net: Multimodal VoxelNet for 3D Object Detection
- Blog: AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons
- Blog: PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration
- Blog: Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models
- Blog: FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
- Blog: Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion
- Blog: PointPainting: Sequential Fusion for 3D Object Detection
- Blog: PointSee: Image Enhances Point Cloud
- Blog: SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
- Blog: Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning
- Blog: CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer
- Blog: Loop Closure Detection with RGB-D Feature Pyramid Siamese Networks
- Blog: MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection
- Blog: 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds
- Blog: Voxel-informed Language Grounding
- Blog: Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video
- Blog: Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting
- Blog: Generative Point Cloud Registration
- Blog: Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement\n Learning
- Blog: Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
- Blog: PanSt3R: Multi-view Consistent Panoptic Segmentation
- Blog: CGR-Block: Correlated Feature Extractor and Geometric Feature Fusion for Point Cloud Analysis
- Blog: CoSSegGaussians: Compact and Swift Scene Segmenting 3D Gaussians with Dual Feature Fusion
- Blog: Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models
- Blog: DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation
- Blog: Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection
- Blog: Deep Learning based 3D Segmentation: A Survey
- Blog: PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
- Blog: A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completion
- Blog: FreePoint: Unsupervised Point Cloud Instance Segmentation
- Blog: KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
- Blog: SAD: Segment Any RGBD
- Blog: CSPC-Dataset: New LiDAR Point Cloud Dataset and Benchmark for Large-Scale Scene Semantic Segmentation
- Blog: Fine-grained Text and Image Guided Point Cloud Completion with CLIP Model
- Blog: PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
- Blog: FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection
- Blog: Vehicle Detection of Multi-source Remote Sensing Data Using Active Fine-tuning Network
- Blog: Pixels2Points: Fusing 2D and 3D Features for Facial Skin Segmentation
Showing 60 of 1,396 papers.
History & citation
Current · Permanent link
- Hybrid 2D and 3D Representations for Spatial Perception merged into this direction (68% overlap)
- Synergistic Fusion of 2D Texture and 3D Geometry merged into this direction (76% overlap)
- Painting 3D Point Clouds with 2D Semantic Features merged into this direction (88% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_modal_feature_fusion_f86bd86c,
title = {cross-modal feature fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-modal-feature-fusion/rdr_f86bd86cb07e41639460aab864547ec2},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_modal_feature_fusion_f86bd86c_v1,
title = {cross-modal feature fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-modal-feature-fusion/rdr_f86bd86cb07e41639460aab864547ec2/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}