Vladimir Yugay
@vyuga3d.bsky.social
Doing research in 3D Computer Vision.
Ph.D. student at the University of Amsterdam. Previously at TUM.
https://vladimiryugay.github.io/
Ph.D. student at the University of Amsterdam. Previously at TUM.
https://vladimiryugay.github.io/
I remember discussing this approach with you in Milano!
October 9, 2025 at 7:29 PM
I remember discussing this approach with you in Milano!
Thanks to the team, Kien Nguyen, Theo Gevers, @cgmsnoek.bsky.social, and @martin-r-oswald.bsky.social from the University of Amsterdam!
October 7, 2025 at 9:02 AM
Thanks to the team, Kien Nguyen, Theo Gevers, @cgmsnoek.bsky.social, and @martin-r-oswald.bsky.social from the University of Amsterdam!
We experimented with different backbones, camera pose representations, scalability, and attention mechanisms. Our evaluation spans hundreds of full-length videos across various metrics, without aligning the predicted trajectory to the ground truth, to simulate a real-world application
October 7, 2025 at 9:02 AM
We experimented with different backbones, camera pose representations, scalability, and attention mechanisms. Our evaluation spans hundreds of full-length videos across various metrics, without aligning the predicted trajectory to the ground truth, to simulate a real-world application
VoT does not require calibration or post-optimization and operates in real-time, capable of processing thousands of frames. It is trained on a vast amount of real-world indoor data, but can work just fine in outdoor scenarios. It uses only camera poses as supervision, making it broadly accessible
October 7, 2025 at 9:02 AM
VoT does not require calibration or post-optimization and operates in real-time, capable of processing thousands of frames. It is trained on a vast amount of real-world indoor data, but can work just fine in outdoor scenarios. It uses only camera poses as supervision, making it broadly accessible
Will you release the slides?👀 They're superb
June 24, 2025 at 7:28 PM
Will you release the slides?👀 They're superb
I will be presenting our previous work at CVPR Nashville. Drop by if you want to chat!
June 10, 2025 at 12:06 PM
I will be presenting our previous work at CVPR Nashville. Drop by if you want to chat!
This work was conducted in collaboration wit Kersten Thies, @lucacarlone.bsky.social , Theo Gevers, @martin-r-oswald.bsky.social , and Lukas Schmid at the Computer Vision Group of the University of Amsterdam and the SPARKLab of @mit.edu
June 10, 2025 at 12:06 PM
This work was conducted in collaboration wit Kersten Thies, @lucacarlone.bsky.social , Theo Gevers, @martin-r-oswald.bsky.social , and Lukas Schmid at the Computer Vision Group of the University of Amsterdam and the SPARKLab of @mit.edu
We evaluate our method on synthetic and real-world datasets that undergo significant changes, including the movement, removal, and addition of large pieces of furniture, cutlery, a coffee machine, and pictures on the walls
June 10, 2025 at 12:06 PM
We evaluate our method on synthetic and real-world datasets that undergo significant changes, including the movement, removal, and addition of large pieces of furniture, cutlery, a coffee machine, and pictures on the walls
GaME detects scene changes and directly manipulates the 3D Gaussians to keep the map up to date. Additionally, our keyframe management system identifies and eliminates pixels that observe stale geometry, thereby minimizing the amount of discarded information
June 10, 2025 at 12:06 PM
GaME detects scene changes and directly manipulates the 3D Gaussians to keep the map up to date. Additionally, our keyframe management system identifies and eliminates pixels that observe stale geometry, thereby minimizing the amount of discarded information
We found two main problems. First, the 3D Gaussian maps can not easily “optimize out” changes in the geometry on the fly. Second, frames observing the old state of the scene contaminate the optimization process, resulting in visual artifacts and inconsistencies
June 10, 2025 at 12:06 PM
We found two main problems. First, the 3D Gaussian maps can not easily “optimize out” changes in the geometry on the fly. Second, frames observing the old state of the scene contaminate the optimization process, resulting in visual artifacts and inconsistencies
Imagine you want ot create a 3DGS map of your apartment. You reconstructed your kitchen and continued to the bedroom. While you are in the bedroom, someone has moved the chair and added a table in the kitchen without telling you. That’s what can happen with your reconstruction👇
June 10, 2025 at 12:06 PM
Imagine you want ot create a 3DGS map of your apartment. You reconstructed your kitchen and continued to the bedroom. While you are in the bedroom, someone has moved the chair and added a table in the kitchen without telling you. That’s what can happen with your reconstruction👇
🔹@rerun.io visualisation script for easy debugging, analysis, and replaying of reconstruction results with minimal effort
March 19, 2025 at 6:47 PM
🔹@rerun.io visualisation script for easy debugging, analysis, and replaying of reconstruction results with minimal effort
🔹Fully Pythonic pose graph optimisation module. The core library live coding by the author is tremendously enlightening www.youtube.com/watch?v=yXWk...
Live coding Graph SLAM in Python (Part 1)
YouTube video by Jeff Irion
www.youtube.com
March 19, 2025 at 6:47 PM
🔹Fully Pythonic pose graph optimisation module. The core library live coding by the author is tremendously enlightening www.youtube.com/watch?v=yXWk...
🔹Place recognition module based on a large vision model - no more annoying dependency chains for DBoVW or NetVLAD
March 19, 2025 at 6:47 PM
🔹Place recognition module based on a large vision model - no more annoying dependency chains for DBoVW or NetVLAD
🔹Simple yet efficient mechanism for correcting and merging multiple 3D Gaussian Splatting maps into a global map
March 19, 2025 at 6:47 PM
🔹Simple yet efficient mechanism for correcting and merging multiple 3D Gaussian Splatting maps into a global map
🔹DinoV2-based place recognition module - no more annoying dependency chains of DBoVW or NetVLAD
March 19, 2025 at 6:35 PM
🔹DinoV2-based place recognition module - no more annoying dependency chains of DBoVW or NetVLAD
🔹A simple yet efficient mechanism for correcting and merging multiple 3D Gaussian Splatting sub-maps into a global map
March 19, 2025 at 6:35 PM
🔹A simple yet efficient mechanism for correcting and merging multiple 3D Gaussian Splatting sub-maps into a global map
Fantastic work! Can't wait to try it out!
February 26, 2025 at 8:56 AM
Fantastic work! Can't wait to try it out!
It feels like a tighter bubble on bsky. It also seems that the more people are aligned, the less they engage
February 8, 2025 at 3:19 PM
It feels like a tighter bubble on bsky. It also seems that the more people are aligned, the less they engage
Ye ye. Or monst3r-project.github.io. One can use them as a prior for dynamic envs just like mast3r for static ones
MonST3R: A Simple Approach for Estimating Geometry in the Presense of Motion
monst3r-project.github.io
December 18, 2024 at 10:23 AM
Ye ye. Or monst3r-project.github.io. One can use them as a prior for dynamic envs just like mast3r for static ones
There's so much progress in there partially bc *3r and splats are inexpensive. GPU poor can iterate fast :)
December 18, 2024 at 10:20 AM
There's so much progress in there partially bc *3r and splats are inexpensive. GPU poor can iterate fast :)