Kavisha Vidanapathirana

PhD student @QUT and @CSIRORobotics. Research Intern @TheAIML. Robotic vision.

[Pieter Abbeel @pabbeel]

Great ICLR 2024 talk on "The Emerging Science of Benchmarks" by Moritz Hardt (which I somehow didn't see, till now):

https://t.co/JYscNt8nBc

[Navinda Kottege @navindak]

Great to be attending @ieee_ras_icra #ICRA2024 in beautiful Yokohama with @CSIRORobotics colleagues and affiliates. @peymanm @ProfKulic @girlinrobotics @MiladRamezani14 @Stephen_Hausler @KavishaVid

[Peyman Moghadam @peymanm]

Next: We are presenting at #ICRA2024 SpectralGV: a registration-free ptcloud re-ranking for realtime lidar metric localization. Led by @KavishaVid collaboration between EmbodiedAI cluster at @CSIRORobotics and @QUT

Paper: https://t.co/TVC5v5N45B
Code: https://t.co/nR3jfEwr1B

[Andrea Tagliasacchi @taiyasaki]

📢📢📢 𝐁𝐀𝐍𝐅: 𝐁𝐚𝐧𝐝-𝐥𝐢𝐦𝐢𝐭𝐞𝐝 𝐍𝐞𝐮𝐫𝐚𝐥 𝐅𝐢𝐞𝐥𝐝𝐬 𝐟𝐨𝐫 𝐋𝐞𝐯𝐞𝐥𝐬 𝐨𝐟 𝐃𝐞𝐭𝐚𝐢𝐥 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 lead by Ahan Shabanov (@ahan_sh) at #CVPR2024

Wonder how to get frequency control in neural fields?
This is for you: https://t.co/Gb1YyJWJTI

[Eric Brachmann @eric_brachmann]

📢A new learning-based approach to SfM: #ACEZero

No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images.

Paper: https://t.co/Zc83YpoXpY
Page: https://t.co/kutgb81eFV

[Kavisha Vidanapathirana @KavishaVid]

Had a great time attending 3DV - my first in-person conference since starting my PhD.

Thanks @3DVconf team for the amazing program and location.

[Chelsea Finn @chelseabfinn]

We introduce a system for fine-grained robotic manipulation! 🤖

What’s new?
* We can control cheap robots to do surprisingly dexterous tasks
* New technique that allows robots to learn fine motor skills

A short thread 🧵

[CSIRORobotics @CSIRORobotics]

We are thrilled to have 4 x papers accepted at @ICRA2023 #icra2023 ICRA will bring together the world's top academics, researchers, and industry representatives on Robotics and Automation. Papers are research collaborations with @Caltech @QUT @MIT_CSAIL @CSIRO's Machine Learning.

[Sameer Singh @ ACL 2026 @sameer_]

These are a really good set of ideas, there will be useful insights here for researchers at any level. Strongly recommended reading!

[CSIRORobotics @CSIRORobotics]

Group photo! This has most of our @CSIRORobotics members and robots but not all. How many robots can you #spot (pun intended!)? #QCAT @navindak @Data61news @Jon_Whittle_ @fredpauling @peymanm

[Kavisha Vidanapathirana @KavishaVid]

Check out my presentation at the @AirLabCMU General Place Recognition Challenge at #ICRA2022 @ieee_ras_icra. I present our method which won 2nd place in the City-scale UGV Localization task.

Thanks @peymanm and @MiladRamezani14. @CSIRORobotics

https://t.co/Rqy2bN8xOa

[AirLab @AirLabCMU]

Our Round 1 General Place Recognition (GPR) Challenge at @ieee_ras_icra was a success with 168 competitors around the world, and received 529 submissions in just 24 days. We also had talks from @lucacarlone1 (MIT), @maththrills (QUT) and @junyanz89(CMU).
https://t.co/SliZPwDWp1

[Yuki Shirai @ ICRA2026 @Yuki_Doradora]

Handshake #ICRA2022

[CSIRORobotics @CSIRORobotics]

Thank you @Data61news for highlighting our success on the world stage. 🥳Kudos to team @MiladRamezani14 @KasraKhosoussi Gavin Catt and @fredpauling @peymanm for #WildcatSLAM
@KavishaVid @MiladRamezani14 and @peymanm for LoGG3D-Net in Collaboration w/ @QUT

[Kavisha Vidanapathirana @KavishaVid]

@KasraKhosoussi @AirLabCMU @ieee_ras_icra @CSIRORobotics @peymanm @MiladRamezani14 Thanks @KasraKhosoussi

[Kavisha Vidanapathirana @KavishaVid]

Excited to share that I'll be presenting at the @AirLabCMU GPR Competition at #ICRA2022 @ieee_ras_icra.

Our method LoGG3D-Net ranked 2nd in round-1 of the City-scale UGV Localization task. Check out our project page: https://t.co/Qw1FC4u4Bm @CSIRORobotics

[AirLab @AirLabCMU]

This year, we host the General Place Recognition competition at #ICRA2022, tackling challenging localization in long-term and large-scale autonomy. There's 2 tracks:
1) City-scale Localization (3D)
2) Visual Terrain Relative Navigation (2D)
For more info: https://t.co/e2mkCKEWeA

[CSIRORobotics @CSIRORobotics]

We are proud to announce our team LoGG3D-Net led by @KavishaVid won the 2nd place at #icra2022 General Place Recognition Competition @peymanm @MiladRamezani14 @QUT @Data61news https://t.co/9ZcoBteNIo

[CSIRORobotics @CSIRORobotics]

Our team CSIRO-Wildcat won the 2022 Hilti SLAM Challenge at @ieee_ras_icra #ICRA2022 @Data61news @Jon_Whittle_ @Hiltigroup @MiladRamezani14 @peymanm @fredpauling @KasraKhosoussi Gavin Catt