Tomáš Hodaň

Research Scientist at Meta

[Tomáš Hodaň @tomhodan]

With @ma_sundermeyer, Vineet Bhat, Jonathan Tremblay, @yashvarpatel, Mederic Fourmy, Stephen Tyree, Junwen Huang, Varun Burde, Martin Cífka, @vaheta, Kirill Zaitsev, @eric_brachmann, Bertram Drost, Carsten Steger, @VincentLepetit2, @BirchfieldStan, @Carsten_Rother, @matas_jiri

[Tomáš Hodaň @tomhodan]

📢 11th R6D workshop on Sep 8 at ECCV'26 in Malmö!
https://t.co/Xc6BnNJUTC

🛝 This year focused on visual grounding capabilities of vision-language models (VLMs)

📊 New BOP-Refer benchmark on 2D/3D grounding

📄 Paper submission deadline: July 24

[Tomáš Hodaň @tomhodan]

Co-organizing the 1st Sense of Space Workshop at CVPR 2026!

Focused on multi-sensory modeling for embodied AI, this year with a special focus on dexterous human-object manipulation.

Call for papers with a submission deadline on March 11.

[Rao Fu @RaoFu79761158]

🚨 Embodied AI still lacks a true “Sense of Space” — 🖐️touch, 💪 force, 🧠 proprioception, 🔊 audio, 👃 smell, ❤️ bio-signals, 🌡️ thermal.

Submit & join the 1st Sense of Space Workshop @CVPR 2026 🏔️✨
🔗 https://t.co/4DmVK1peb7

We tackle it from two directions:
⬆️ Bottom-up: 🧩 emergent new sensors & systems
⬇️ Top-down: 🤖🖐️ dexterous hand–object manipulation from multisensory inputs

📣 Call for Papers: proceedings + non-proceedings
Accepted papers can apply for ✈️ travel grants + 🏆 sponsored paper awards.

Powered by an amazing organizing team 💥🤝
@RaoFu79761158 @LiGuankfd2 @alex_kai2020 Kun He @tomhodan Ergys Ristani Jessica Yin @AntheaYLi @yining_hong Devin Murphy Ray Song @xyz2maureen @ericyi0124 Qi Ye @YunzhuLiYZ @haoshu_fang @ruoshi_liu Vatsal Mehta @LuoYiyue @MengyuLearner @wojmatusik

[Rao Fu @RaoFu79761158]

🚨 Embodied AI still lacks a true “Sense of Space” — 🖐️touch, 💪 force, 🧠 proprioception, 🔊 audio, 👃 smell, ❤️ bio-signals, 🌡️ thermal.

Submit & join the 1st Sense of Space Workshop @CVPR 2026 🏔️✨
🔗 https://t.co/4DmVK1peb7

We tackle it from two directions:
⬆️ Bottom-up: 🧩 emergent new sensors & systems
⬇️ Top-down: 🤖🖐️ dexterous hand–object manipulation from multisensory inputs

📣 Call for Papers: proceedings + non-proceedings
Accepted papers can apply for ✈️ travel grants + 🏆 sponsored paper awards.

Powered by an amazing organizing team 💥🤝
@RaoFu79761158 @LiGuankfd2 @alex_kai2020 Kun He @tomhodan Ergys Ristani Jessica Yin @AntheaYLi @yining_hong Devin Murphy Ray Song @xyz2maureen @ericyi0124 Qi Ye @YunzhuLiYZ @haoshu_fang @ruoshi_liu Vatsal Mehta @LuoYiyue @MengyuLearner @wojmatusik

[Giovanni M Farinella @GMFarinella]

ICVSS 2026
Sicily ~ 5-11 july 2026

Computer vision for spatial and physical intelligence

Applications are open - Deadline 1 April 2026
https://t.co/YFGBD7oc8D

LIST OF SPEAKERS
https://t.co/9mE9GP5Lbg

@robertocipolla @sebattiato @GMFarinella

[Tomáš Hodaň @tomhodan]

10th (!!) R6D workshop @ ICCV 2025: https://t.co/bFx9WxizlG

🤖 Object pose estimation for industrial robotics

📢 Strong speakers: @svlevine, @haoshu_fang, @MaxlDur , @GusKalra , @vaheta

📊 BOP Challenge 2025 with new BOP-Industrial datasets

With @ma_sundermeyer

[Take Ohkawa @tkhkaeio]

Huge thanks!! I'm glad to have been a part of your wonderful work, Assembly101!
I really appreciate your help: Kun, @famesener, @tomhodan, Luan, Cem, and my advisor Yoichi!
#EgoVis

[Vahe Taamazyan @vaheta]

Had a great PIRA workshop at CVPR, thanks to Vincent Vanhoucke, Kartik Iyer, @bowenwen_me, Kartik Venkataraman, and @tomhodan

[Tomáš Hodaň @tomhodan]

Happy to announce a new bin-picking challenge with $60,000 in prizes! Organized by OpenCV, Intrinsic, BOP, Orbbec, and University of Hawaii at Manoa.

[OpenCV - Open Source Computer Vision Library @opencvlive]

Submissions for the $60,000 Challenge begin February 1st, team registration begins now. Don't miss your chance to be featured in a CVPR workshop. Learn more at https://t.co/w8Ln3Xfpvn and good luck! #OpenCV #ComputerVision #AI #OpenSource #Robotics #CVPR2025

[TechXplore @TechXplore_com]

#Meta introduces HOT3D, an open-source #Dataset featuring 3D egocentric videos for advanced computer vision. This resource enhances robot manipulation and human-machine interface research. Available on Project Aria. @arxiv https://t.co/VXmkLxDFBy https://t.co/F7PoS0OXx1

[Sammy Joe Christen @sammy_j_c]

A model that generates hand-object interactions based on text prompts!

I'm happy to share our @SIGGRAPHAsiapaper “DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions”.
https://t.co/JbKosU1cHl

[Tomáš Hodaň @tomhodan]

📽️ Recording of the 9th Workshop on Recovering 6D Object Pose (R6D): https://t.co/CdOGhFV7Qg

The workshop was held at ECCV 2024 and featured four invited talks (@XiaoweiZhou5, @BusamBenjamin, @BirchfieldStan, @jajuengel) and a presentation of the BOP Challenge 2024.

[Evin Pınar Örnek @evinpinar]

🚀 We present FoundPose at #ECCV2024 in Milan! 🇮🇹

📌 FoundPose is a model-based method for 6D pose estimation of unseen objects from a single image, without any task/object-specific training!

📅 Thu, 10:30 AM – 12:30 p.m., poster #280

🌐 Project Page: https://t.co/fwi3tfgfIU

Work done @RealityLabs, with @tomhodan, @cem_keskin_, @LingniMa, Bugra Tekin, Yann Labbé, Christian Forster. @eccvconf

[Oriane Siméoni @CVPR @oriane_simeoni]

Poster #72 #ECCV2024 is already up and running with @mkwysoczanska @MichaelRamamon @abursuc. Come by if you want to talk about open-vocabulary semantic segmentation at low cost!

[Tomáš Hodaň @tomhodan]

📈 BOP update: Deadline for the 2024 challenge is extended to November 29!

BOP'24 focuses on model-free and model-based 2D/6D object detection, and introduces three new datasets from Meta and NVIDIA – HOT3D, HOPEv2, and HANDAL.

https://t.co/5nWv125raN

[Tomáš Hodaň @tomhodan]

We are releasing 🔥HOT3D🔥, a new egocentric dataset for 3D hand and object tracking.

833 minutes (3.7M images) of multi-view image streams showing 19 subjects interacting with 33 objects, annotated with high-quality 3D poses of hands and objects.

Paper: https://t.co/9mKrH4aZKQ

[Edward Miller @TweetEdMiller]

Introducing, HOT3D.

HOT3D is a new dataset from our team at Meta Reality Labs Research, to explore vision-based methods for hand-object interaction.

https://t.co/AR39UbhwgD

1/

[Martin Sundermeyer @ma_sundermeyer]

The new BOP challenge 2024 pushes model-free and generalizable 6D object pose estimation. 🏆

Learn about the current state of 6D object pose estimation and the next challenges by visiting our poster at the mixed reality workshop (10:30-11:15) #CV4MR at #CVPR2024 📷

[vannguyen @vannguyen_ng]

📢 Benchmark for 6D Object Pose Estimation 📢

BOP challenge 24 has been opened!

https://t.co/Od5U0LGzS9

Results to be presented at the R6D workshop at #ECCV2024

Details in comments below👇

[Martin Sundermeyer @ma_sundermeyer]

One highlight were the new BOP challenge results: For the first time we evaluated unseen object pose estimation, i.e. methods that generalize without expensive retraining. Here is a summary of the latest progress 🚀

https://t.co/XzhFismmc2

[Martin Sundermeyer @ma_sundermeyer]

Missed the #ICCV2023 Workshop on Recovering 6D Object Pose? #R6D

Find all recordings here:
https://t.co/A6flIFkrnR

Thanks to @tomhodan @yann_labbe and all speakers for the new insights!