Xin Lin

PhD student@UCSD
Computer Vision, 3DV, Panoramic Vision.

[Yuheng Liu @yuhengliu02]

𝘕𝘢𝘳𝘳𝘰𝘸 𝘷𝘪𝘦𝘸𝘴 𝘭𝘪𝘮𝘪𝘵 𝘸𝘰𝘳𝘭𝘥 𝘮𝘰𝘥𝘦𝘭𝘪𝘯𝘨.

[𝟭/𝟭𝟬] We are excited to introduce our 𝑺𝑰𝑮𝑮𝑹𝑨𝑷𝑯 2026 work 𝐎𝐦𝐧𝐢𝐑𝐨𝐚𝐦 — a framework for long-horizon panoramic video generation 🌍

It enables controllable scene wandering from a single image or short video.

Project Page: https://t.co/eaQPdrX6MJ

Github: https://t.co/uLY9SEagte

arXiv: https://t.co/T3WRxOylbk

@AdobeResearch

[Ziyi Wu @Dazitu_616]

📢Introducing 360Anything, our method for lifting any perspective image or video to gravity-aligned 360° panoramas without using any camera or 3D information. This enables consistent novel view synthesis and 3D scene reconstruction.

Project page: https://t.co/qTOEip0Jw2

🧵

[William Yijiang Li @Williamiumli]

🚨Announcing our #ICLR2026 Workshop, The First Workshop on Efficient Spatial Reasoning (ES-Reasoning) @iclr_conf

🚀 Call for Papers!!!
We accept Regular (9 pages) and Tiny (4 pages) papers!!
Timeline:
📅 Deadline: 2026/02/09, 11:59PM AOE
📣 Acceptance notification: 2026/03/01

🌐Learn more at our Website: https://t.co/H4lpdiFhPQ

Kudos to our amazing co-organizers @zhijianliu_ @ManlingLi_ @robinluo1997 @SeerePan @Besteuler @ruiyang_qin

@ucsd_cse @UCSDJacobs @HDSIUCSD @CUHKofficial @VillanovaU @NorthwesternU

[Baiang Li @MotaLee5]

Welcome to the LowLevel CV platform!
https://t.co/s5ulwBTY76
This platform focuses on low-level computer vision research, continuously integrating community resources such as papers, datasets, competitions, and workshops, and updating recruitment information from institutions.

[Xin Lin @XinLin321]

Thanks for sharing!

[DailyPapers @HuggingPapers]

Insta360 Research unveils Depth Any Panoramas

A new foundation model for panoramic depth estimation, excelling across diverse scenes and distances. It achieves robust, metrically consistent predictions in real-world scenarios.

[DailyPapers @HuggingPapers]

Insta360 Research unveils Depth Any Panoramas

A new foundation model for panoramic depth estimation, excelling across diverse scenes and distances. It achieves robust, metrically consistent predictions in real-world scenarios.

[Xin Lin @XinLin321]

Depth Any Panoramas!
DAP is an open, real-world–generalized metric depth model, providing a strong foundation for spatial understanding in AIGC and real-world modeling.
🔗 https://t.co/4xHG3y5wlS
📄 https://t.co/CYLkaoWi0P
🎮 https://t.co/BHk1itcjOq

[Haodong Li @haodongli00]

Thanks @_akhaliq for sharing our work! The code and demo will be public soon. Please have a look if you are interested.🥰🥰🥰

Paper: https://t.co/rywt2tPEKz, https://t.co/2b4lEhKk05
Github: https://t.co/0i6CIqpxLC
Project page: https://t.co/z7tL4nBWjn

[AK @_akhaliq]

DA^2

Depth Anything in Any Direction

[Xin Lin @XinLin321]

@33yuliangguo Very impressive work! We will include a discussion of it in our next revision.

[Xin Lin @XinLin321]

🌍 World model? Virtual embodied worlds? Immersive experiences?
Panoramic vision unlocks infinite possibilities! 🚀
We just released our new survey🔥:
“One Flight Over the Gap: A Survey from Perspective to Panoramic Vision” 🌐📷

🔗 Project page: https://t.co/I3qu2To7HA

[Xin Lin @XinLin321]

3. ✨ Let’s shape the future of panoramic vision together!

[Xin Lin @XinLin321]

2. Covering 20+ representative tasks (super-resolution, segmentation, generation, multimodal, etc.), we summarize key strategies and insights.
We hope this work provides a clear knowledge map while advancing panoramic vision in world models, VR, autonomous driving, and robotics.

[Xin Lin @XinLin321]

1. We systematically review 300+ studies on panoramic vision, from imaging systems and projections to cross-method/task analyses and future trends. We highlight three challenges in perspective to panorama adaptation:
Geometric distortion
Non-uniform sampling
Boundary continuity