CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks

[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies

Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.

A multi-modal network to do open vocabulary seach and semantic segmentation over 3D scenes

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

Query-Time Refinement for Open-Vocabulary 3D Instance Segmentation

Our OpenYOLO3D model achieves state-of-the-art performance in Open Vocabulary 3D Instance Segmentation on ScanNet200 and Replica datasets with up ∼16x speedup compared to the best existing method …

Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)

[NeurIPS 2023] Weakly Supervised 3D Open-vocabulary Segmentation

[CVPR 24] MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation

😎 up-to-date & curated list of awesome 3D Visual Grounding papers, methods & resources.

[ICCV 2021] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding [ACM MM'21]

[AAAI 2024] Mono3DVG: 3D Visual Grounding in Monocular Images, AAAI, 2024

[ECCV 2020] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language

[AAAI 2024] EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

[CVPR 2023] EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

[ACM MM-2024] RefMask3D: Language-Guided Transformer for 3D Referring Segmentation

[ECCV'24] OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

[ECCV 2024] MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo

Official code for "Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle" (CVPR 2024)

[CVPR 2024] This repo contains the code for our paper: Rethinking Few-shot 3D Point Cloud Semantic Segmentation

https://arxiv.org/abs/2104.02246 One Thing One Click (CVPR 2021) https://arxiv.org/abs/2303.14727 One Thing One Click++ (Arxiv)

Cross-Modal Unsupervised Domain Adaptationfor 3D Semantic Segmentation

Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud (AAAI 2021)