Lists (2)
Stars
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
[ECCV 2024] 3D World Model for Autonomous Driving
[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.
[Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving
[CVPR 2024] SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction
This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
Code release for NeRF (Neural Radiance Fields)
LiDAR Image Pretraining for Visual Place Recognition
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation
A paper list of RGBD semantic segmentation (processing)
[CVPR 2025]DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation && [ICLR 2024] DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
MUSt3R: Multi-view Network for Stereo 3D Reconstruction
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
Official implementation of Continuous 3D Perception Model with Persistent State
MonoDINO-DETR: Depth-Enhanced Monocular 3D Object Detection Using a Vision Foundation Model
[ICCV2023] GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
Code release for Revisit Anything: Visual Place Recognition via Image Segment Retrieval (ECCV 2024)
Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.…
"Omnidirectional CNN for Visual Place Recognition and Navigation", ICRA 2018
Official code for CVPR 2022 (Oral) paper "Deep Visual Geo-localization Benchmark"