![](/rp/kFAqShRrnkQMbH6NYLBYoJ3lq9s.png)
Matias Turkulainen - Google Scholar
Esa Rahtu Professor, Tampere University, Finland Verified email at tuni.fi. Follow. Matias Turkulainen. Aalto University, ETH Zurich. Verified email at aalto.fi - Homepage. computer vision computer graphics. Articles Cited by Co-authors. Title. …
Matias Turkulainen
Matias Turkulainen, Xuqian Ren, Iaroslav Melekhov, Otto Seiskari, Juho Kannala, Esa Rahtu. Winter Conference on Applications of Computer Vision (WACV), 2025. arXiv ProjectPage Github
Matias Rahtu (FIN1987M1)
First Name: Matias: Last Name: RAHTU: Nationality: FIN: Place of Birth: Rovaniemi FIN: Date of Birth: 01 Dec 1987: Age: 36: Gender: male: Athlete ID: FIN1987M1 ...
Matias Turkulainen, Xuqian Ren, Iaroslav Melekhov, Otto Seiskari, Esa Rahtu, Juho Kannala. Winter Conference on Applications of Computer Vision (WACV), 2025. AGS-Mesh: Adaptive Gaussian Splatting and Meshing with Geometric Priors for …
[2403.17822] DN-Splatter: Depth and Normal Priors for Gaussian ...
Mar 26, 2024 · High-fidelity 3D reconstruction of common indoor scenes is crucial for VR and AR applications. 3D Gaussian splatting, a novel differentiable rendering technique, has achieved state-of-the-art novel view synthesis results with high rendering speeds and …
AGS-Mesh : Adaptive Gaussian Splatting and Meshing with …
Overview: We present AGS-Mesh, a method that adaptively integrates geometric priors into Gaussian Splatting for indoor room reconstruction using a mobile device. Sensor depth and normal filter. Mesh comparison: Novel view synthesis on real-world indoor scenes: MuSHRoom dataset with iPhone data.
GitHub - maturk/dn-splatter: DN-Splatter + AGS-Mesh: Depth …
This repo implements research papers (DN-Splatter and AGS-Mesh) for depth and normal supervision of Gaussian splatting models for improved novel-view synthesis using smartphone data (iPhones) and mesh reconstruction. Quick demo:
Gaussian Splatting on the Move: Blur and Rolling Shutter …
Mar 20, 2024 · We present a method that adapts to camera motion and allows high-quality scene reconstruction with handheld video data suffering from motion blur and rolling shutter distortion. Our approach is based on detailed modelling of the physical image formation process and utilizes velocities estimated using visual-inertial odometry (VIO).
Matias Rahtu (M) - openpowerlifting.org
Apr 3, 2019 · Place Fed Date Location Competition Division Age Equip Class Weight Squat Bench Deadlift Total Dots; 1: SVNL: 2017-05-13: Finland: Kansallinen klassinen voimanostokilpailu
GitHub Pages - Profile
Nov 1, 2023 · Currently I am a PhD student at Computer Vision Group, Tampere University, where I am working with and supervised by Prof. Esa Rahtu and Prof. Juho Kannala from Aalto University on Novel View Synthesis, 3D Reconstruction & Generation and Video Generation. I am open to collaborations and internships.