Xin Kong's picture

Xin Kong

kxic

·

https://kxhit.github.io/

AI & ML interests

3D Computer Vision, Robotics, SLAM

Recent Activity

authored a paper about 5 hours ago

Cosmos 3: Omnimodal World Models for Physical AI

upvoted a paper about 1 year ago

Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

liked a Space about 1 year ago

View all activity

Organizations

Papers 3

arxiv:2606.02800

arxiv:2402.03908

arxiv:2302.01838

spaces 1

EscherNet

3D novel view synthesis from any number images!

models 8

kxic/EscherNet_demo

Updated Oct 28, 2024 • 4

kxic/eschernet-4dof

Updated Feb 29, 2024 • 339 • 1

kxic/eschernet-6dof

Updated Feb 29, 2024 • 134 • 1

kxic/stable-zero123

Updated Jan 28, 2024 • 15

kxic/sd-v1-5

Text-to-Image • Updated Sep 21, 2023 • 2

kxic/zero123-165000

Updated Aug 2, 2023 • 29 • 2

kxic/zero123-xl

Updated Aug 2, 2023 • 576 • 2

kxic/zero123-105000

Updated Aug 2, 2023 • 4 • 2

datasets 5

kxic/EscherNet-Dataset

Preview • Updated Sep 10, 2024 • 22

kxic/Objaverse_zero123_lvis_subset

Updated Apr 13, 2024 • 23 • 3

kxic/Objaverse_zero123_wds

Viewer • Updated Apr 4, 2024 • 113 • 360 • 1

kxic/EscherNet-Results

Preview • Updated Feb 5, 2024 • 4

kxic/vMAP

Preview • Updated Feb 21, 2023 • 313 • 2