daveredrum / ScanRefer
[ECCV 2020] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
☆229Updated last year
Related projects: ⓘ
- [CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans☆99Updated 2 years ago
- ☆130Updated last month
- [ICCV 2021] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextua…☆72Updated 2 years ago
- Code accompanying our ECCV-2020 paper on 3D Neural Listeners.☆108Updated 3 years ago
- Implementation for ECCV 2022 paper Language-Grounded Indoor 3D Semantic Segmentation in the Wild☆99Updated last year
- 3RScan Toolkit☆184Updated 2 years ago
- Code for CVPR 2021 oral paper "Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts"☆221Updated 2 years ago
- A collection of 3D vision and language (e.g., 3D Visual Grounding, 3D Question Answering and 3D Dense Caption) papers and datasets.☆95Updated last year
- [ICCV'21] Pri3D: Can 3D Priors Help 2D Representation Learning?☆149Updated 2 years ago
- CVPR2023 : VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud☆59Updated 2 months ago
- Code for the ECCV22 paper "Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds"☆74Updated last year
- Official PyTorch code of Holistic 3D Scene Understanding from a Single Image with Implicit Representation (CVPR 2021). Also includes a Py…☆198Updated 3 years ago
- Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)☆236Updated last year
- Hierarchical Aggregation for 3D Instance Segmentation (ICCV 2021)☆164Updated last year
- Implementation of "Bidirectional Projection Network for Cross Dimension Scene Understanding" CVPR 2021 (Oral)☆169Updated 3 years ago
- (CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learn…☆251Updated 2 months ago
- Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction☆204Updated 5 months ago
- [ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning☆222Updated last year
- Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs☆57Updated last year
- Official code release of "CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition"☆214Updated last year
- Group-Free 3D Object Detection via Transformers☆242Updated 3 years ago
- [ECCV'24] OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation☆127Updated last week
- Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"☆192Updated 7 months ago
- ☆99Updated last year
- [CVPR 2021] Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis (official pytorch implementation)☆49Updated 2 years ago
- [CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation☆159Updated last year
- Official implementation of Language Conditioned Spatial Relation Reasoning for 3D Object Grounding (NeurIPS'22).☆50Updated last year
- [NeurIPS 2022 Spotlight] P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting☆126Updated last year
- The data skeleton from "3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera" http://3dscenegraph.stanford.edu☆240Updated 2 months ago
- Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes☆51Updated last year