FanScy / BEVInstructor
[ECCV24] Navigation Instruction Generation with BEV Perception and Large Language Models
☆20Updated 2 months ago
Related projects: ⓘ
- [ECCV 2024] 4D Contrastive Superflows are Dense 3D Representation Learners☆34Updated this week
- [CVPR 2024] Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding☆36Updated last month
- [CVPR 2024] This is official implementation of our CVPR 2024 paper "Building a Strong Pre-Training Baseline for Universal 3D Large-Scale …☆11Updated 3 months ago
- ☆51Updated 10 months ago
- [ECCV 2024] Monocular Occupancy Prediction for Scalable Indoor Scenes☆19Updated last week
- ☆31Updated 2 months ago
- Project Page for GaussianFormer☆19Updated 3 months ago
- officical code for ECCV 2024 paper "Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection"☆10Updated 2 months ago
- Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model☆39Updated 3 months ago
- Open-Vocabulary SAM3D: Understand Any 3D Scene☆24Updated 2 weeks ago
- Official code of "Segment any 3D Object with Language"☆35Updated 4 months ago
- [CVPR24] Depth Prompting for Sensor-Agnostic Depth Estimation☆22Updated last month
- [CVPR 2024 Highlight] OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies☆39Updated 4 months ago
- [AAAI 2024] SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection☆34Updated 5 months ago
- ☆34Updated 10 months ago
- [CVPR 2024] Situational Awareness Matters in 3D Vision Language Reasoning☆13Updated 2 months ago
- Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding☆42Updated 5 months ago
- ☆21Updated last month
- This is the official implementation of "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels" (Accepted at C…☆22Updated 3 months ago
- ☆28Updated last month
- Multi-Space Alignments Towards Universal LiDAR Segmentation☆33Updated 2 months ago
- [CVPR 2023] MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training☆47Updated last year
- Code, dataset and models for our CVPR 2022 publication "Text2Pos"☆38Updated 2 years ago
- [CVPR 2024] Memory-based Adapters for Online 3D Scene Perception☆78Updated last week
- [NeurIPS 2022] 4D Unsupervised Object Discovery☆52Updated 9 months ago
- ☆24Updated 2 months ago
- (AAAI2024) Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models☆42Updated 4 months ago
- [NeurIPS 2023] Weakly Supervised 3D Open-vocabulary Segmentation☆102Updated 8 months ago
- Official implementation of Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation (CoRL'24).☆27Updated last week
- [CVPR 2024] DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement☆37Updated 6 months ago