Omar Alama عمر الأعمى
@OmarAlama
ECE Vision and Robot Perception PhD @ Carnegie Mellon University
Want to push the online 🌎 understanding & search capabilities of robots? Introducing RayFronts 🌟→ 💡 Semantics within & beyond depth sensing 🏃♂️ Online & real-time mapping 🔍 Querying with images & text ⚙️ Operating in any environment rayfronts.github.io The trick →🧵👇
RayFronts code has been released ! github.com/RayFronts/RayF… 🤖 Guide your robot with semantics within & beyond depth. 🖼️ Stop using slow SAM crops + CLIP pipelines. RayFronts gets dense language aligned features in one forward pass. 🚀 Test your mapping ideas in our pipeline !
![OmarAlama's tweet card. [IROS 2025] Source code for "RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration" - RayFronts/RayFronts](https://pbs.twimg.com/card_img/1948109402038587392/UwmNEV78?format=jpg&name=orig)
أول ورقة بحثية لي في مسيرة الدكتوراه. فكرة المشروع ببساطة اعطاء الروبوت او الدرون المقدرة على فهم جميع الأشياء من حوله في أي بيئة. بحيث تقدر تسأل الروبوت بأي نص أو أي صورة عن أي شيء شافه. اذا كان الشيء داخل اطار احساسه بالمسافة فحيقدر يحدد مكانه بدقة. وان كان أبعد فيحدد اتجاهه.
Want to push the online 🌎 understanding & search capabilities of robots? Introducing RayFronts 🌟→ 💡 Semantics within & beyond depth sensing 🏃♂️ Online & real-time mapping 🔍 Querying with images & text ⚙️ Operating in any environment rayfronts.github.io The trick →🧵👇
Getting tired of visual language navigation in indoor environments? Check RayFronts🏹, open-set semantic mapping for beyond depth-sensing-range observations.
Want to push the online 🌎 understanding & search capabilities of robots? Introducing RayFronts 🌟→ 💡 Semantics within & beyond depth sensing 🏃♂️ Online & real-time mapping 🔍 Querying with images & text ⚙️ Operating in any environment rayfronts.github.io The trick →🧵👇
Super excited about this work pushing the boundary of online semantic mapping!! One step closer to making robots see the world 🌎🚀 Check out Omar's thread for a lot more eye candy 🤩 and impressive results!
Want to push the online 🌎 understanding & search capabilities of robots? Introducing RayFronts 🌟→ 💡 Semantics within & beyond depth sensing 🏃♂️ Online & real-time mapping 🔍 Querying with images & text ⚙️ Operating in any environment rayfronts.github.io The trick →🧵👇
Want to learn how to empower 🤖 with real-time scene understanding and exploration capabilities? Catch Me, @hocherie1 & @QiuYuhengQiu presenting RayFronts at #RSS2025 SemRob Workshop (OHE 122) & Epstein Plaza at 10:00 am PST Today!
Excited to present RayFronts in IROS25 in Hangzhou !Never been to China before !
We're excited to share that five papers from AirLab 🚀have been accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025! Papers are on the thread:
I was waiting for the AI to make a mistake the whole time. Was shocked by the quality. It was even simplifying new concepts introduced in our paper with analogies. Really impressive tool @NotebookLM Listen to the full podcast here youtu.be/_tIVlw1Wrh4?si…
Very surprised by the quality of podcast style overviews generated by @NotebookLM. The RayFronts team tried them out and we were amazed by the quality and accuracy of the explanation. Some couldn't tell if it was AI generated. Should the AirLab start its own podcast channel? 📷
#ICRA2025 alert! 🚨🥳 Congratulations to Yuheng Qui, Yutian Chen, Zihao Zhang, Wenshan Wang, and Sebastian Scherer on winning the Best Conference Paper Award for: "MAC-VO: Metrics-Aware Covariance for Leaning-Based Stereo Visual Odometry"! #CMUrobotics arxiv.org/abs/2409.09479
🚀 Thrilled to present ViSafe, a vision-only airborne collision avoidance system that achieved drone-to-drone avoidance at 144 km/h. In an era of congested airspace and growing autonomy, reliable self-separation is paramount 🧵👇
نمط متكرر. الناس تكتشف أسئلة بسيطة جدا النماذج اللغوية مثل ChatGpt تفشل في الجواب عليها. الشركات القائمة على النماذج تنتبه، تعيد تدريب النموذج ليجاوب بشكل صحيح. الناس تنبهر وتقول الآن صار فاهم. وتنعاد الحلقة. الواقع هو ان النماذج اللغوية الى الآن تنطبق عليها مقولة "حافظ مش فاهم".
At what point should it be reasonable to expect coherent answers to these? How far beyond PhD-level reasoning must we climb?
SIGLIP wins over CLIP even in dense tasks like zero shot open-vocab semantic segmentation on Replica . Using the RayFronts encoder (NA attention + RADIO @PavloMolchanov + SIGLIP @giffmana) projection to the CLS token gives you SoTA performance. No more SAM+CROP+CLIP business.
