iiinova — where your digital self keeps evolving

Saqib @sjaved.bsky.social · 31/07/2025

🚀More good news: our paper SE-GS is accepted as an oral at ICCV 2025 🥳📸 Gaussian Splatting gets another boost 🌈 Code’s out, camera-ready coming soon! 🔗 lnkd.in/gprqxNjq #ICCV2025 #GaussianSplatting #3DVision #3Dreconstruction #rendering

000

Saqib @sjaved.bsky.social · 09/05/2025

📢 Excited to share my first conference paper got into #ICML2025! 🎉 QT-DoG: Quantization-Aware Training for Domain Generalization Huge thanks to Mathieu salzmann and Hieu Le for their support 🙏 🔗 saqibjaved1.github.io/QT_DoG/ #ML #AI #DeepLearning #quantization #CV

saqibjaved1.github.io

QT-DOG: QUANTIZATION-AWARE TRAINING FOR DOMAIN GENERALIZATION

QT-DoG: QUANTIZATION-AWARE TRAINING FOR DOMAIN GENERALIZATION

010

Reposted by Saqib

Pascal @pvfua.bsky.social · 11/04/2025

Lab outing at the local Archery Center. I imagine some of us were thinking about Reviewer #2. It helps with accuracy ;-)

182

Saqib @sjaved.bsky.social · 10/04/2025

Had a great time giving a talk at Magic Leap on "Real-Time Dynamic 3D Scenes: Temporal Compression of Gaussian Representations"! Shared our TC3DGS work and exciting future directions in 3D vision! 🚀 🌐 ahmad-jarrar.github.io/tc-3dgs/ #3DReconstruction #GaussianSplatting #ComputerVision #ARVR

ahmad-jarrar.github.io

TC3DGS

Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes

010

Saqib @sjaved.bsky.social · 19/12/2024

✨Our recent work introduces compressed dynamic 3D Gaussian representations: TC3DGS! TC3DGS utilizes temporal pruning, mixed-precision quantization, & trajectory interpolation—all with minimal quality loss!🚀 🌐 Page: ahmad-jarrar.github.io/tc-3dgs #3DReconstruction #DynamicScenes #GaussianSplatting

010

Saqib @sjaved.bsky.social · 19/12/2024

🚀 Do check out our latest work on Modular Mixed-precision Quantization! 🌐 Page: saqibjaved1.github.io/MQAT_/ #Quantization #Mixedprecision #DeepLearning #Robotics #AI #6Dpose #edgeAI

020

Saqib @sjaved.bsky.social · 16/12/2024

🚀 Excited to share our TMLR publication on Modular Quantization-Aware Training (MQAT)! We show how modular mixed-precision quantization boosts performance & reduces model size for edge devices! 🎯 🌐 Page: saqibjaved1.github.io/MQAT_/ #DeepLearning #Robotics #AI #6Dpose #edgeAI

230