Stars
Extrapolated Urban View Synthesis Benchmark
Official PyTorch implementation of 3D Gaussian Mapping (3DGM)
This is the official code release for our work, Denoising Vision Transformers.
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
Occ4cast: LiDAR-based 4D Occupancy Completion and Forecasting
[RSS2023] Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space
[IROS2024] SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
[ICCV 2023] Among Us: Adversarially Robust Collaborative Perception by Consensus
[CVPR2023] DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
Full conference version of AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]
[ICRA 2023] Uncertainty Quantification of Collaborative Detection for Self-Driving
Self-supervised place recognition by exploring temporal and feature neighborhoods
[ECCV2022] Official Implementation of paper "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer"
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
An SDK for multi-agent collaborative perception.
[CVPR 2022] Egocentric Action Target Prediction in 3D
Unsupervised Domain Adaptation for Nighttime Aerial Tracking (CVPR2022)
[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image
[NeurIPS2021] Learning Distilled Collaboration Graph for Multi-Agent Perception
[ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.
Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks
[ICRA2014] Fast Plane Extraction Using Agglomerative Hierarchical Clustering (AHC)
[IROS2021] NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences