Pinned Tweet
(1/8)
We are excited to share our new model ARROW 🏹 !
ARROW brings D4RT-style decoding to broader input types, including multi-view videos and unordered collections of images.
📜arXiv: arxiv.org/abs/2610.01314
🌐Project page: vision.rwth-aachen.de/arrow
Ilya Fradlin retweeted
Excited to share our latest work, VINO! 🍷
We redesigned self-supervised representation learning for 3D scenes with the Volume Transformer and closed the gap to supervised representations 🚀
Need DINO for 3D/volumetric data?
Check out: 🍷VINO: Revisiting 3D Representation Learning with Volume Transformers
📝arxiv.org/abs/2611.07176
🏠adriankruse.github.io/VINO/
Great collab w/ @adr_kruse @KadirYilmaz_CV @dcdegeus @BastianLeibe
@RWTHVisionLab @USI_INF @TUeindhoven1
🖥️ Alongside ARROW’s inference code, we’ve also released a dedicated interactive viewer!
You can run inference directly from there and view the predictions in 3D, we’ve tried to make it as intuitive and easy to use as possible. 👀
🔗 Give it a try: github.com/ifradlin/arrow
Original post 👇🏼
nitter.cf/ifradlin/status/210607…
(1/8)
We are excited to share our new model ARROW 🏹 !
ARROW brings D4RT-style decoding to broader input types, including multi-view videos and unordered collections of images.
📜arXiv: arxiv.org/abs/2610.01314
🌐Project page: vision.rwth-aachen.de/arrow
147
🚀Code is now available!
🔗 github.com/ifradlin/arrow
(1/8)
We are excited to share our new model ARROW 🏹 !
ARROW brings D4RT-style decoding to broader input types, including multi-view videos and unordered collections of images.
📜arXiv: arxiv.org/abs/2610.01314
🌐Project page: vision.rwth-aachen.de/arrow
(7/8)
📊 ARROW achieves state-of-the-art results across multiple tasks:
• WorldTrack: best APD/EPE on all 4 datasets.
• TAPVid-3D: best APD/AJ, surpassing the current SOTA D4RT.
• Strong multi-view tracking, and competitive 3D reconstruction, depth & pose estimation.
1
5
512
(8/8)
Additional details:
🌐 Project: vision.rwth-aachen.de/arrow
📄 arXiv: arxiv.org/abs/2610.01314
🐙 Code: github.com/ifradlin/arrow
This work wouldn’t have been possible without @thecschmidt4, @piekenbrinck, @karimknaebel, @gomartingarcia, and @BastianLeibe - huge thanks! 🙌🏼
6
517
Ilya Fradlin retweeted
Challenge-maxxing at #CVPR2026 with my buddy @adr_kruse , using our recent 3D backbone Volt ⚡️
We won 3 challenges at this CVPR and I’ll present Volt at the ScanNet++ (@chandan__yes) and OpenSUN3D(@FrancisEngelman) workshops on the first day afternoon (June 3rd). Come by!
Could this be the ViT moment for 3D scene understanding? 🚀
We revisit the good old Transformer architecture and apply it to 3D scene understanding with minimal modifications. #Volt ⚡️
Project page: yilmazkadir.github.io/Volt/
Arxiv link: arxiv.org/abs/2604.19609
(1/5)
Ilya Fradlin retweeted
New work: SurGe
We improve local accuracy in feedforward 3D reconstruction. Current point map models struggle with bending and oscillating artifacts for thin structures (chair legs, street lamps, etc). Easy to spot visually, but not well captured by pointwise metrics like AbsRel.
Ilya Fradlin retweeted
Could this be the ViT moment for 3D scene understanding? 🚀
We revisit the good old Transformer architecture and apply it to 3D scene understanding with minimal modifications. #Volt ⚡️
Project page: yilmazkadir.github.io/Volt/
Arxiv link: arxiv.org/abs/2604.19609
(1/5)
Ilya Fradlin retweeted
🔥 EoMT now supports DINOv3! 🔥
✨ Upgrading DINOv2 to DINOv3 consistently improves image segmentation performance
⚡ Lightning-fast inference with EoMT's minimalist design
📦 Model weights and code available! 🔗 github.com/tue-mps/eomt
Ilya Fradlin retweeted
I'll be presenting "DINO in the Room (DITR)", the winning method of the ScanNet++ 3D semantic segmentation challenge, tomorrow at CVPR at 10 a.m. in Room 211.
Project page: visualcomputinginstitute.git…
Ilya Fradlin retweeted
Happening now at #CVPR2025 🎉If you wonder #Interactive4D Lidar segmentation, visit our poster at Hall D with the poster number 134 👩🏼💻🤖
🌎Project Page: ilya-fradlin.github.io/Inter…
@iFradlin @idilzulfikar @KadirYilmaz_CV @DoraKontog @BastianLeibe
Ilya Fradlin retweeted
Happy to share that #Interactive4D got accepted to #ICRA2025🥳
Also, the code is now available🤓💻
@iFradlin @KadirYilmaz_CV @DoraKontog @BastianLeibe
🌐Project: ilya-fradlin.github.io/Inter…
📜Paper: arxiv.org/pdf/2410.08206
🚀Check our recent work #Interactive4D to achieve interactive #LiDAR segmentation of multiple objects on multiple scans simultaneously. Work with Ilya Fradlin, @KadirYilmaz_CV, @DoraKontog, and @BastianLeibe. 🌐Project: ilya-fradlin.github.io/Inter…
📜Paper: arxiv.org/pdf/2410.08206👇🧵
Ilya Fradlin retweeted
🚀Check our recent work #Interactive4D to achieve interactive #LiDAR segmentation of multiple objects on multiple scans simultaneously. Work with Ilya Fradlin, @KadirYilmaz_CV, @DoraKontog, and @BastianLeibe. 🌐Project: ilya-fradlin.github.io/Inter…
📜Paper: arxiv.org/pdf/2410.08206👇🧵













