London, UK

Xin Kong

Expert
@kxhit

Research Scientist at NVIDIA Cosmos Lab @nvidia-cosmos. PhD from Imperial College London @dyson-robotics-lab. World Model, GenAI, Spatial AI, Robotics.

kxhit.github.io/

awesome-point-cloud-place-recognition. A list of papers about point cloud based place recognition, also known as loop closure detection in SLAM (processing)

410

EscherNet. [CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

377

vMAP. [CVPR 2023] vMAP: Vectorised Object Mapping for Neural Field SLAM

372

SG_PR. Implementation of IROS20 paper - "Semantic Graph Based Place Recognition for 3D Point Clouds"

204

zero123-hf. A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)

154

semantic-icp. fork from https://bitbucket.org/saparkison/semantic-icp/src

45

pointnetvlad. Add KITTI and Ford datasets support to PointNetVLAD (CVPR18) https://github.com/mikacuy/pointnetvlad

23

cvpr25_oral_gpu_info. Just wanna see what type and how many GPUs/TPUs are used in CVPR 2025 oral papers. Fun vibe coding with LLMs.

12

BDCI2018-pointnet-. This is the source code for BDCI-2018 阿里巴巴自动驾驶三维点云语义分割 of our team (试一下pointnet)

6

google-landmark. Dataset with 5 million images depicting human-made and natural landmarks spanning 200 thousand classes.

2

Hierarchical-Localization. Visual localization made easy

1

SqueezeSegV2. Implementation of SqueezeSegV2, Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

1

GN-Net-Benchmark. Additional Code for the GN-Net benchmark. The data is available at http://vision.in.tum.de/gn-net

1

Landmark2019-1st-and-3rd-Place-Solution. The 1st Place Solution of the Google Landmark 2019 Retrieval Challenge and the 3rd Place Solution of the Recognition Challenge.

1
14
Apply