Xiangting (Martin) Meng

ShanghaiTech University, Mobile Perception Lab

[Xiangting (Martin) Meng @ArnoMeng]

I switched to Codex and coding feels different now.
It doesn’t just suggest snippets. It understands the repo, edits files, and helps carry work from idea to implementation.
Codex feels less like autocomplete and more like a real engineering teammate.
#SwitchToCodex #Codex

[Tibo @thsottiaux]

Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched?

Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens!

https://t.co/8mU93eA13i

[Xiangting (Martin) Meng @ArnoMeng]

Our Paper has accepted on CVPR26

[Zhenjun Zhao @zhenjun_zhao]

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

Zicheng Zhang, Xiangting Meng, Ke Wu, Wenchao Ding

tl;dr: Shannon entropy->adaptive sampling; 3D KNN-> local info.->GS

https://t.co/fsYcqZCPIb

[Xiangting (Martin) Meng @ArnoMeng]

Our Paper has accepted on ICLR26

[Zhenjun Zhao @zhenjun_zhao]

Flash-Mono: Feed-Forward Accelerated Gaussian Splatting Monocular SLAM

Zicheng Zhang, Ke Wu, Xiangting Meng, Keyu Liu, Jieru Zhao, Wenchao Ding

tl;dr: recurrent FF->pose+2DGS; hidden state->Sim(3) optimization->loop closure

https://t.co/n3LVkcoHlw

[Zhenjun Zhao @zhenjun_zhao]

SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction

Zicheng Zhang, Xiangting Meng, Ke Wu, Wenchao Ding

tl;dr: Shannon entropy->adaptive sampling; 3D KNN-> local info.->GS

https://t.co/fsYcqZCPIb

[Xiangting (Martin) Meng @ArnoMeng]

@mzubairirshad look forward to it.

[Xiangting (Martin) Meng @ArnoMeng]

🎉 Excited to share that Prof. Laurent Kneip will personally present our paper “DynOPETs” at #ICCV2025, Hawaii!
Pre ⏰ & 📍 Oct 20, 11:50–12:10, Room 234
You can also find our poster at Exhibit Hall II, Oct 20, 4:20–5:30 PM (Board #179).
Code Page: https://t.co/S2St803Jm5

[Xiangting (Martin) Meng @ArnoMeng]

Meng et al. DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarios
Paper link: https://t.co/k4wKAbK1ZH
Project page: https://t.co/Gtsq28ugXX

[Xiangting (Martin) Meng @ArnoMeng]

Video link：https://t.co/wB1NAvSB4U
Paper link：https://t.co/k4wKAbK1ZH

[Xiangting (Martin) Meng @ArnoMeng]

We propose DynOPETs, a dataset for dynamic object pose estimation with both category- and instance-level labels in scenes with moving cameras.
Enabled by an efficient pipeline combining pose tracking, estimation, and PGO.
Benchmarked on 18 SOTA methods，
https://t.co/Gtsq28ugXX

[Xiangting (Martin) Meng @ArnoMeng]

@wuke20010216 🤣

[Xiangting (Martin) Meng @ArnoMeng]

Great work, the first kilometers level GS visual inertial/ mono GS SLAM!

[MrNeRF @janusch_patas]

VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes

Note: Mesh is created from Kitty dataset.

Contributions:
• We are the first monocular (inertial) GS-based SLAM system capable of operating outdoors and supporting kilometer-scale urban scenes.

• We propose a 2D Gaussian Map module, including a sample rasterizer, score manager, and single-to-multi pose refinement, ensuring accurate localization and high-quality Gaussian maps in real time.

• We introduce a GS-based loop detection method, along with an efficient approach that corrects tens of millions of Gaussian attributes in a single operation upon loop detection, effectively eliminating accumulated errors and ensuring global map consistency.

• Comprehensive experiments on different scenes (indoor environments, aerial drone view, and driving scenes) demonstrate that VINGS-Mono outperforms existing approaches in rendering and localization performance. We also developed a mobile app and conducted real-world experiments to demonstrate the practical reliability of our method.

[Xiangting (Martin) Meng @ArnoMeng]

Great work!!!!! Truly Large scale!!

[Xiangting (Martin) Meng @ArnoMeng]

Wu et al. VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenes
https://t.co/jbCgK53q1g
Shared by: https://t.co/UKAeo3E282