Iro Armeni
@ir0armeni.bsky.social
Assistant Prof. Stanford CEE | Gradient 𝚫 Spaces Group. Researching #VisualMachinePerception to transform #Design & #Construction | http://gradientspaces.stanford.edu
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
🌐 rectified-pointflow.github.io
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
🌐 rectified-pointflow.github.io
July 8, 2025 at 8:47 PM
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
🌐 rectified-pointflow.github.io
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
🌐 rectified-pointflow.github.io
🌟🏆 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: goo.gle/rs
Details and this year’s cohort of exceptional researchers: goo.gle/rs
Research scholar program
Overview
goo.gle
June 25, 2025 at 5:59 PM
🌟🏆 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: goo.gle/rs
Details and this year’s cohort of exceptional researchers: goo.gle/rs
🚨Only 1 day left to submit a full paper on (scene) graphs to the 3rd Workshop on #SG2RL!
- Can't make it? Extended abstracts are due on July 7th
- Dangling carrot🥕? We are in 𝑯𝒂𝒘𝒂𝒊'𝒊, @ICCVConference 2025
🌐 sites.google.com/view/sg2rl/
- Can't make it? Extended abstracts are due on July 7th
- Dangling carrot🥕? We are in 𝑯𝒂𝒘𝒂𝒊'𝒊, @ICCVConference 2025
🌐 sites.google.com/view/sg2rl/
SG2RL
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 wi...
sites.google.com
June 25, 2025 at 5:44 PM
🚨Only 1 day left to submit a full paper on (scene) graphs to the 3rd Workshop on #SG2RL!
- Can't make it? Extended abstracts are due on July 7th
- Dangling carrot🥕? We are in 𝑯𝒂𝒘𝒂𝒊'𝒊, @ICCVConference 2025
🌐 sites.google.com/view/sg2rl/
- Can't make it? Extended abstracts are due on July 7th
- Dangling carrot🥕? We are in 𝑯𝒂𝒘𝒂𝒊'𝒊, @ICCVConference 2025
🌐 sites.google.com/view/sg2rl/
At @cvprconference.bsky.social? 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!
gradientcanvas.github.io
Gradients Spaces, Stanford Univ.
It is a community generated #AR painting. Users can claim a region and add their own contribution. No painting skills required, just words!
gradientcanvas.github.io
Gradients Spaces, Stanford Univ.
June 14, 2025 at 10:08 PM
At @cvprconference.bsky.social? 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!
gradientcanvas.github.io
Gradients Spaces, Stanford Univ.
It is a community generated #AR painting. Users can claim a region and add their own contribution. No painting skills required, just words!
gradientcanvas.github.io
Gradients Spaces, Stanford Univ.
At @cvprconference.bsky.social? 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
(1/4)
▶️ Talk at 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics
📅 Wed June 11th, 11:15-11:45AM
📍 106C
June 11, 2025 at 1:39 AM
At @cvprconference.bsky.social? 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
(1/4)
▶️ Talk at 5th Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics
📅 Wed June 11th, 11:15-11:45AM
📍 106C
Reposted by Iro Armeni
📰 Paper: arxiv.org/abs/2502.15011
▶️ Project Page: sayands.github.io/crossover/
💻 Codebase: github.com/GradientSpaces…
Work w/ Ondrej Miksik, @marcpollefeys.bsky.social, @danielbarath.bsky.social and @ir0armeni.bsky.social ✨
(3/3)
▶️ Project Page: sayands.github.io/crossover/
💻 Codebase: github.com/GradientSpaces…
Work w/ Ondrej Miksik, @marcpollefeys.bsky.social, @danielbarath.bsky.social and @ir0armeni.bsky.social ✨
(3/3)
June 10, 2025 at 7:55 PM
📰 Paper: arxiv.org/abs/2502.15011
▶️ Project Page: sayands.github.io/crossover/
💻 Codebase: github.com/GradientSpaces…
Work w/ Ondrej Miksik, @marcpollefeys.bsky.social, @danielbarath.bsky.social and @ir0armeni.bsky.social ✨
(3/3)
▶️ Project Page: sayands.github.io/crossover/
💻 Codebase: github.com/GradientSpaces…
Work w/ Ondrej Miksik, @marcpollefeys.bsky.social, @danielbarath.bsky.social and @ir0armeni.bsky.social ✨
(3/3)
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
🌐 respace.mnbucher.com
w/ @mnbucher.bsky.social
- Object addition = next-token prediction
- RLVR-tuned for fine control
- Voxel loss for geometric nuance
🌐 respace.mnbucher.com
w/ @mnbucher.bsky.social
✨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)
**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)
June 4, 2025 at 9:59 PM
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
🌐 respace.mnbucher.com
w/ @mnbucher.bsky.social
- Object addition = next-token prediction
- RLVR-tuned for fine control
- Voxel loss for geometric nuance
🌐 respace.mnbucher.com
w/ @mnbucher.bsky.social
🎨 AI-powered interior design from video—just bring a Pinterest image.
Meet ReStyle3D #SIGGRAPH25: per-object, multi-view style transfer for real scenes.
No 3D model. No camera poses. Just semantics + diffusion magic.
🚀 Stylize scenes, photorealistically.
🌐 restyle3d.github.io
Meet ReStyle3D #SIGGRAPH25: per-object, multi-view style transfer for real scenes.
No 3D model. No camera poses. Just semantics + diffusion magic.
🚀 Stylize scenes, photorealistically.
🌐 restyle3d.github.io
🔔 Want to redesign your apartment and control the style of every piece of furniture? (virtual try-on for 3D scenes).
🎨 Introducing ReStyle3D, a method that transforms your apartment into the design styles as you want! #stylization #SIGGRAPH
Page: restyle3d.github.io
Code: github.com/GradientSpac...
🎨 Introducing ReStyle3D, a method that transforms your apartment into the design styles as you want! #stylization #SIGGRAPH
Page: restyle3d.github.io
Code: github.com/GradientSpac...
May 27, 2025 at 6:20 PM
🎨 AI-powered interior design from video—just bring a Pinterest image.
Meet ReStyle3D #SIGGRAPH25: per-object, multi-view style transfer for real scenes.
No 3D model. No camera poses. Just semantics + diffusion magic.
🚀 Stylize scenes, photorealistically.
🌐 restyle3d.github.io
Meet ReStyle3D #SIGGRAPH25: per-object, multi-view style transfer for real scenes.
No 3D model. No camera poses. Just semantics + diffusion magic.
🚀 Stylize scenes, photorealistically.
🌐 restyle3d.github.io
🚨 Winners of the Nothing Stands Still Challenge 2025 are in!
🥇First Place: Daebeom Kim, Seungjae Lee, Seoyeon Jang, Jei Kong, Prof. Hyun Myung
🥈Second Place: Xuan Ouyang, Linjie Li, Zhengbao Wang, Prof. Siwen Quan, Prof. Jiaqi Yang
Congrats! 🏗️✨
#ICRA2025 #NSS
🥇First Place: Daebeom Kim, Seungjae Lee, Seoyeon Jang, Jei Kong, Prof. Hyun Myung
🥈Second Place: Xuan Ouyang, Linjie Li, Zhengbao Wang, Prof. Siwen Quan, Prof. Jiaqi Yang
Congrats! 🏗️✨
#ICRA2025 #NSS
Nothing Stands Still — Except the Date!
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
May 21, 2025 at 8:56 PM
Nothing Stands Still — Except the Date!
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
May 18, 2025 at 8:46 PM
Nothing Stands Still — Except the Date!
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
Join us May 19 (Atlanta or Zoom) for the 4th Workshop on Construction Robotics!
Explore 4D perception, automation, & results from the #NothingStandsStill challenge.
Info: construction-robots.github.io
#ConstructionRobotics #4DPerception
🚨 👉 NSS Challenge deadline extended to **May 12th**-- spread the word!
🏗️ Nothings Stands Still Challenge 2025
🌐 www.nothing-stands-still.com/challenge
4th Workshop on Future of Construction, ICRA 2025
May 19th, Atlanta, USA
construction-robots.github.io
#NSS #ICRA2025
🏗️ Nothings Stands Still Challenge 2025
🌐 www.nothing-stands-still.com/challenge
4th Workshop on Future of Construction, ICRA 2025
May 19th, Atlanta, USA
construction-robots.github.io
#NSS #ICRA2025
May 6, 2025 at 5:35 PM
🚨 👉 NSS Challenge deadline extended to **May 12th**-- spread the word!
🏗️ Nothings Stands Still Challenge 2025
🌐 www.nothing-stands-still.com/challenge
4th Workshop on Future of Construction, ICRA 2025
May 19th, Atlanta, USA
construction-robots.github.io
#NSS #ICRA2025
🏗️ Nothings Stands Still Challenge 2025
🌐 www.nothing-stands-still.com/challenge
4th Workshop on Future of Construction, ICRA 2025
May 19th, Atlanta, USA
construction-robots.github.io
#NSS #ICRA2025
🚨 SLAM struggling in dynamic environments? We've been there.
WildGS-SLAM at #CVPR2025, our new monocular RGB SLAM system, tackles dynamic scenes with uncertainty-aware tracking and mapping, resulting to more robust tracking, cleaner maps, and high-quality view synthesis. ⬇️
🌐 wildgs-slam.github.io
WildGS-SLAM at #CVPR2025, our new monocular RGB SLAM system, tackles dynamic scenes with uncertainty-aware tracking and mapping, resulting to more robust tracking, cleaner maps, and high-quality view synthesis. ⬇️
🌐 wildgs-slam.github.io
🥳Excited to share our latest work, WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments, accepted to #CVPR2025 🌐
We present a robust monocular RGB SLAM system that uses uncertainty-aware tracking and mapping to handle dynamic scenes.
We present a robust monocular RGB SLAM system that uses uncertainty-aware tracking and mapping to handle dynamic scenes.
April 11, 2025 at 7:15 PM
🚨 SLAM struggling in dynamic environments? We've been there.
WildGS-SLAM at #CVPR2025, our new monocular RGB SLAM system, tackles dynamic scenes with uncertainty-aware tracking and mapping, resulting to more robust tracking, cleaner maps, and high-quality view synthesis. ⬇️
🌐 wildgs-slam.github.io
WildGS-SLAM at #CVPR2025, our new monocular RGB SLAM system, tackles dynamic scenes with uncertainty-aware tracking and mapping, resulting to more robust tracking, cleaner maps, and high-quality view synthesis. ⬇️
🌐 wildgs-slam.github.io
The Nothing Stands Still Challenge is back and due on ⌛ May 7th!
💰 Kept the cash prize but created new data that are extra challenging.
🏗️ Goal: create spatiotemporal maps of drastically changing environments. What a better fit than construction sites?
Visit here:
🌐 hilti-challenge.com
💰 Kept the cash prize but created new data that are extra challenging.
🏗️ Goal: create spatiotemporal maps of drastically changing environments. What a better fit than construction sites?
Visit here:
🌐 hilti-challenge.com
March 6, 2025 at 6:31 PM
The Nothing Stands Still Challenge is back and due on ⌛ May 7th!
💰 Kept the cash prize but created new data that are extra challenging.
🏗️ Goal: create spatiotemporal maps of drastically changing environments. What a better fit than construction sites?
Visit here:
🌐 hilti-challenge.com
💰 Kept the cash prize but created new data that are extra challenging.
🏗️ Goal: create spatiotemporal maps of drastically changing environments. What a better fit than construction sites?
Visit here:
🌐 hilti-challenge.com
How do you align point clouds, CAD, floor plans. images, and text to share scene knowledge?
CrossOver learns a unified, modality-agnostic embedding space—enabling seamless multi-modal scene alignment without semantic labels.
#CVPR2025
🌐sayands.github.io/crossover/
CrossOver learns a unified, modality-agnostic embedding space—enabling seamless multi-modal scene alignment without semantic labels.
#CVPR2025
🌐sayands.github.io/crossover/
February 27, 2025 at 8:52 PM
How do you align point clouds, CAD, floor plans. images, and text to share scene knowledge?
CrossOver learns a unified, modality-agnostic embedding space—enabling seamless multi-modal scene alignment without semantic labels.
#CVPR2025
🌐sayands.github.io/crossover/
CrossOver learns a unified, modality-agnostic embedding space—enabling seamless multi-modal scene alignment without semantic labels.
#CVPR2025
🌐sayands.github.io/crossover/