“Senna VFX Breakdown by Picma Creative Post Picma Post shares the excitement as Senna races to the top of Netflix’s global non-English series chart! Collaborating with Netflix, director Vicente Amorim, and a talented team, Picma delivered stunning VFX for this heartfelt project.
https://x.com/vfxexpress/status/1867103608195453130
“”Xreal One smart glasses are powered by an on-device chip — and I got the chance to try them on” – @tomsguide Link to Article ⤵️
https://x.com/XREAL_Global/status/1865441144655794494
“The future of sports broadcasting is volumetric. Combine this 3d tech with advances in object detection & tracking, and you can tap a button to follow the ball or even a specific player. Split screen + stats + social for the full experience. Cant wait!
https://x.com/bilawalsidhu/status/1867704947799986608
“BREAKING: Just when you thought the Google news was over, there’s more! Android XR is officially official – the Gemini era is coming to VR headsets and AR glasses. Here’s the latest, w/o the hype. Let’s get into it 🧵
https://x.com/bilawalsidhu/status/1867238069101076672
“Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.
https://x.com/jin_linyi/status/1867402868833366307
“Binocular Overlap on MeganeX Superlight 8K is outstanding! And that is so important for immersion. Watch the whole podcast episode here:
https://x.com/mixedrealityTV/status/1866207211648668087
Scientists call for all-out, global effort to create an AI virtual cell | Stanford Report
https://news.stanford.edu/stories/2024/12/scientists-call-for-all-out-global-effort-to-create-an-ai-virtual-cell
“🚀 Introducing SimVS: our new method that simplifies 3D capture! 🎯 3D reconstruction assumes consistency—no dynamics or lighting changes—but reality constantly breaks this assumption. ✨ SimVS takes a set of inconsistent images and makes them consistent with a chosen frame.
https://x.com/alextrevith/status/1866683858592162175
“Excited to introduce Proc-GS🚀! A new pipeline integrating procedural modeling with 3D-GS to accelerate 3D building creation and infinite city generation with high flexibility and photo-realistic visual quality. -Project:
https://x.com/liyixxxuan/status/1866841261157781710
“🎓 We introduce SAMa! A material selection and segmentation model on 3D models in any format (3DGS, NeRF, Mesh). Given a user click, we propose to select all regions on an objects with the same material. We can also do segmentation in under a minute:
https://x.com/vdeschaintre/status/1866142914885382152
“PanoDreamer: 3D Panorama Synthesis from a Single Image TL;DR: Create 360° 3D scenes from a single image. Contributions: – We propose a novel framework for synthesizing a coherent 3D panoramic scene from a single image. – We formulate the problem of single-image panorama
https://x.com/janusch_patas/status/1866171338253357367
“Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos Contributions: 1) A framework for obtaining real-world, dynamic, and pseudo-metric 4D reconstructions and camera poses at scale from existing online video. 2) DynaDUSt3R, a method that takes a pair of frames
https://x.com/janusch_patas/status/1867511260872683921
PanoDreamer: 3D Panorama Synthesis from a Single Image
https://people.engr.tamu.edu/nimak/Papers/PanoDreamer/index.html
Gaussian Splatting and Nerfs
“Recently, I’ve been working a lot on Gaussian Splatting. I built a repo for camera pose estimation using @rerundotio, @Gradio, and @prefix_dev that merges GLOMAP with hloc! 🧵More info below
https://x.com/pablovelagomez1/status/1866157894749835685
“LineGS : 3D Line Segment Representation on 3D Gaussian Splatting Chenggang Yang, Yuang Shi, Wei Tsang Ooi tl;dr: 3DGS tend to be dense along the edges -> so they can help filtering & post processing the lineclouds.
