Iro Armeni
@ir0armeni
Followers
2K
Following
556
Media
66
Statuses
323
Assistant Prof @Stanford CEE | Gradient 𝚫 Spaces Group. Researching #VisualMachinePerception to transform #Design & #Construction | https://t.co/27cilI29Bt
Joined June 2018
Just dropped: Rectified Point Flow.Can we automate 3D assembly from unposed point clouds without supervision?.Yes—we use a generative model that learns symmetry & part interchangeability entirely from shape.Enabling robotics, AR/VR, & reverse engineering.🌐
Point maps have become a powerful representation for image-based 3D reconstruction. What if we could push point maps even further tackle 3D registration and assembly?.Introducing Rectified Point Flow (RPF), a generic formulation for point cloud pose estimation.
1
7
67
🌟🏆 Excited to share that I’ve been selected as a recipient of the 2025 Google Research Scholar Program, on Machine Perception! Grateful to Google Research for supporting early-career faculty. Details and this year’s cohort of exceptional researchers:
research.google
Overview
We’re announcing the 87 professors selected for the 2025 Google Research Scholar Program — join us in congratulating these exceptional recipients and learn more about their groundbreaking work at #GoogleResearch #GoogleResearchScholar.
3
2
49
🚨Only 1 day left to submit a full paper on (scene) graphs to the 3rd Workshop on #SG2RL! Can't make it? Extended abstracts due July 7th. Dangling carrot🥕? We are in 𝑯𝒂𝒘𝒂𝒊'𝒊, @ICCVConference. 🌐🤹w/ the driving force @azadef, & @eadeli, @fedassa.
sites.google.com
Overview The workshop focuses on the topic of scene graphs and graph representation learning for visual perception applications in different domains. Through a series of keynote talks, the audience...
#SG2RL returns to @ICCVConference 2025 at Honolulu, Hawai'i 🌴☀️.We call for full papers and extended abstracts on all topics around graphs and scene graphs. Deadline: 26 June (23:59PT).Website: With our amazing co-organizers: @eadeli @ir0armeni @fedassa.
0
3
8
We are here today till 5:15PM and tomorrow from 10AM. Creators (alphabetically): @ir0armeni, @mnbucher, @debsarkar_sayan, Emily Steiner, Tao Sun, @jianhao75895505, @liyuan_zz.
0
0
0
At @CVPR? Come to the AI Art exhibit to interact with our #GradientCanvas! . It is a community generated #AR painting. Users can claim a region and add their own contribution. No painting skills required, just words!. Gradients Spaces, Stanford Univ.
2
3
14
RT @debsarkar_sayan: 📣 Happening in 30 mins!. Come chat with us about our ✨Highlight ✨ #CVPR paper on 3D scene cross-modal alignment, Cross….
0
4
0
0
5
0
Can’t make it?.Don’t worry, he will present it again on Saturday, Poster 12060, morning session. Also, on Sunday morning during the demo session.
0
0
2
At #CVPR2025? Meet us now and for the next two hours in ExHallD, poster 128! . @jianhao75895505 is presenting his WildGS-SLAM paper, on handling dynamic distractors for static 3D reconstruction. w/ @zhuzihan2000 , Valentin Bieri , @mapo1,@songyoupeng .🌐
At @CVPR? Join me for:.(1/4).▶️ Talk at 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics.📅 Wed June 11th, 11:15-11:45AM.📍 106C
1
2
8
(4/4).▶️Gradient Canvas: An AR Community Art Project.🌐🤹w/ Gradient Spaces Lab (alphab.): @mnbucher, @debsarkar_sayan, Emily Steiner, Tao Sun, @jianhao75895505, @liyuan_zz.📍CVPR AI Art.📅Fri Jun 13th-Sun Jun 15th. Find us and interact with our AR canvas!.
0
0
4
(3/4).▶️ WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments.🌐🤹 w/ @jianhao75895505, @zhuzihan2000, Valentin Bieri, @mapo1, @songyoupeng.📅 Poster #12060, Sat June 14th, 10:30AM-12:30PM.📅 Demo: Sun June 15th, 10:30AM-12:30PM.📍ExHallD.
1
0
3
(2/4).▶️CrossOver: 3D Scene Cross-Modal Alignment.🌐🤹@debsarkar_sayan, Ondrej Miksik, @mapo1, @majti89.📅Highlight Poster #346, Fri June 13th, 4-6PM.📍ExHallD.& 4th Workshop on Open-World 3D Scene Understanding with Foundation Models, June 12th, Poster.
1
0
2
At @CVPR? Join me for:.(1/4).▶️ Talk at 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics.📅 Wed June 11th, 11:15-11:45AM.📍 106C
1
0
9
RT @debsarkar_sayan: ✨ Excited to head off to Nashville for #CVPR2025. 🎤 Catch me at the poster sessions or just come say hi to grab ☕. 🗓️….
0
1
0
Meet 𝐑𝐞𝐒𝐩𝐚𝐜𝐞, a text-driven 3D scene synthesis+editing method, powered by autoregressive LLMs and spatially grounded representations. Object addition = next-token prediction.RLVR-tuned for fine control.Voxel loss for geometric nuance.🌐w/ @mnbucher.
✨What if you could create and redesign scenes by just talking to them? . **ReSpace: Text-Driven 3D Scene Synthesis and Editing with Preference Alignment**. Add, remove, and swap objects simply via natural language, e.g., "add tufted dark gray sofa". (1/8)
1
8
64
RT @FrancisEngelman: What makes a good 3D scene representation? Instead of meshes or Gaussians, we propose Superquadrics to decompose 3D sc….
0
70
0
Topics include:.• Multimodal reasoning & perception.• LM-MM agent behaviors.• Efficient multimodal training.• Evaluation & alignment methods.Submit your work & join the discussion!.#ICCV2025 #MultimodalAI #AIagents #FoundationModels.
0
0
1