ASTRM (@astrm_labs) 's Twitter Profile
ASTRM

@astrm_labs

ASTRM Intelligence Labs

ID: 1935091730392453120

linkhttps://astrm.in calendar_today17-06-2025 21:46:52

13 Tweet

130 Followers

28 Following

I▲N CURTIS (@xrarchitect) 's Twitter Profile Photo

15mb gaussian splat generated from a single Midjourney image running extremely smooth on the web. 2026 will be the year for world models.

rsasaki0109 (@rsasaki0109) 's Twitter Profile Photo

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams Achieving higher reconstruction quality and more accurate camera pose estimation using thousands of frames input. github.com/AutoLab-SAI-SJ… >We propose InfiniteVGGT, a causal visual geometry transformer that

InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
Achieving higher reconstruction quality and more accurate camera pose estimation using thousands of frames input.
github.com/AutoLab-SAI-SJ…
>We propose InfiniteVGGT, a causal visual geometry transformer that
Thomas Richter-Trummer (@pixelbilly) 's Twitter Profile Photo

Capturing Unreal scenes with 360° equirectangular images → fixed-pose COLMAP rig → training becomes much more predictable for #gaussiansplatting. Unreal Capture → COLMAP → Lichtfeld Studio (MCMC Default) → LOD (SOGv2) + FX→ runs on the web and mobile. Demo link in reply

rsasaki0109 (@rsasaki0109) 's Twitter Profile Photo

Pi3MOS-SLAM Dynamic Visual SLAM using a General 3D Prior github.com/PRBonn/Pi3MOS-… Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is

Pi3MOS-SLAM
Dynamic Visual SLAM using a General 3D Prior
github.com/PRBonn/Pi3MOS-…
Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is
Basile Terver (@basileterv987) 's Twitter Profile Photo

My first PhD paper is out! 🎓 "What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?" tl:dr: JEPA-WMs for robotics: learn dynamics on top of visual encoders, optimize actions towards goal 👇 w/ Jimmy (Tsung-Yen) Yang, Jean Ponce, Adrien Bardes, Yann LeCun

Kwang Moo Yi (@kwangmoo_yi) 's Twitter Profile Photo

Zhao and Wei et al., "Spatia: Video Generation with Updatable Spatial Memory" "Memory" for video models via point cloud-conditioned video generation. I am obviously still biased towards having these "explicit" 3D stuff.

rsasaki0109 (@rsasaki0109) 's Twitter Profile Photo

Enhanced SLAM3R: Real-Time Reconstruction via Online Camera Stream github.com/HJCheng0602/SL… This is an enhanced and improved version of the well-known SLAM3R framework, designed to significantly expand its input versatility. The core advancement lies in enabling the use of online

ASTRM (@astrm_labs) 's Twitter Profile Photo

The draft DAP 2026 is a massive win for true deep-tech. By shifting the focus from manufacturing localization to IP ownership and Design Sovereignty, the रक्षा मंत्री कार्यालय/ RMO India is clearing the path for companies like ours that prioritize original engineering over licensed production.