“Augmented reality x-ray vision to “see through” concrete. Your infrastructure won’t just be scanned — it’ll be anchored to reality. Demo: Pix4D reality capture with precise geospatial localization.
“Stop watching videos, start interacting with worlds. Stoked to share CAT4D, our new method for turning videos into dynamic 3D scenes that you can move through in real-time!
“☕ Coffee today with a new AI paper called CAT4D. It’s basically a new way to take a regular 2D video and turn it into a full 4D scene. Think “bullet time” from The Matrix, but now you can move freely through space and time while the scene plays out. The core problem they’re
MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model
EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
“Fluid Reality High Resolution Haptic Glove This glove uses compact Fluid Reality actuator arrays to provide high-resolution haptic feedback in virtual reality, with 20 haptic pixels/cm². The actuators are low-profile, low-power, and self-contained, requiring no external tubing
“Monocular depth estimation has gotten so good lately. It used to look like a blurry blobby flickering mess. Now it looks like a synthetic depth map you’d export from a 3d tool Like putting on a fresh pair of glasses 🤓
“”MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving” Hongsi Liu, Jun Liu, Guangfeng Jiang, Xin Jin abs:
“Microsoft Flight Simulator in VR is an absolutely breathtaking experience!
“Animating virtual cameras can be daunting — but tools like Black Eye given you automatic 3D camera control. It’s like having a virtual camera operator that can deal with complex 3D scenes — with freedom to go back and edit/refine everything in post.
“INMO AIR 3 – The world’s first standalone AR glasses featuring new full-color Sony micro‑OLED displays • 0.44 inch Sony micro‑OLED • 1080p, 120Hz, 62 PPD • Array Waveguide, 600 nits, 36° FoV • Powered by Snapdragon 4nm, 8-core chip • 3DoF, Multi-Window support, Office
Apple Vision Pro
A new update at http://cinemersivelabs.com and at our expo booth at #ECCV2024: improved volumetric photos and videos, an Apple VisionPro photo app, and improved immersive experience for non-VR platforms (desktop and mobile)
Gaussian Splatting and Nerfs
“Wait for it… a 3d timelapse of a real estate project over time. These are snapshots of drone 3d scans created with gaussian splatting and gauzilla pro (gotta love the name).
“Introducing 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧 𝐀𝐧𝐲𝐭𝐡𝐢𝐧𝐠, a new 3D generative model with two key properties: – A structured point-cloud latent space enabling flexible editing! – Support multi-modal conditions, e.g., point cloud, text, single/multi-view images arXiv:
“Thrilled to announce our paper “3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes”, led by Jan Held with @Eng_Hemdi, @AdrienDeliege, @anthony_cioppa, @GiancolaSilvio, Andrea Vedaldi, @BernardSGhanem, Marc Van Droogenbroeck. Page:
“When making city-scale 3D radiance fields are the new kid on the block — but the photogrammetry is still the reality capture OG. Microsoft Flight Simulator 2024 is the perfect case in point. I absolutely love geospatial 3D imagery — especially in virtual reality 😍
“Gassidy: Gaussian Splatting SLAM in Dynamic Environments Long Wen, Shixin Li, Yu Zhang, Yuhong Huang, Jianjie Lin, Fengjunjie Pan, @redrisingeve, Alois Knoll tl;dr: Gaussians->designed photometricgeometric loss->rendering loss flows->dynamic changes
“3D Gaussian Splats are cool, but they’re static (Part 37). GPS-Gaussian+ can render high-resolution 3D scenes from 2 or more input images in real-time! Links ⬇️
“📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian
“I always thought camera pose estimation is necessary for 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and
“Feed-forward 3D Gaussians from @Oxford_VGG strike again! Flash3D has now been accepted to 3DV 2025: it is a method for feed-forward single-view 3D scene reconstruction. Project page:
3D Modeling
“Something about three js 3d graphics running @ 120 fps on an e-ink display just hits different.
“🌟Material Anything🌟 We present Material Anything✨, a diffusion model that can generate photo-realistic PBR materials for any 3D meshes (generated or real). project:
“🔥 3D-LLMs go brrrr! 🚀 Excited to announce our latest research on scaling 3D-LLM training data to *million-scale* with *dense grounding*. 🌟 Introducing 3D-GRAND: a pioneering dataset featuring 40,087 household scenes paired with 6.2 million densely-grounded 3D-text pairs. 🏠💬
“🔥 EFM3D: a new benchmark for 3D egocentric perception tasks The EFM3D benchmark measures progress on egocentric 3D reconstruction and 3D object detection to accelerate research on egocentric foundation models rooted in 3D space. A new model, EVL, establishes the first baseline.
“Dope 3D mapping rig: Leica’s CountryMapper running 31K-pixel array + 2MHz LiDAR with mechanical FMC and 60° FOV. Single-pass co-registered RGB and point clouds that are just ridiculous. And I’m saying this as someone who worked with Google’s street-level LiDAR. Except those
“Introducing 𝐒𝐀𝐑𝟑𝐃, which tokenizes 3D objects into multiscale tokens and generates 3D objects by autoregressive next-scale prediction. 𝐒𝐀𝐑𝟑𝐃 enables fast 3D generation and comprehensive 3D understanding. arXiv:
“🚀 Excited to share our latest paper: “Learning 3D Representations from Procedural 3D Programs” We explore self-supervised learning of 3D representations using procedurally generated shapes, with no reliance on human-designed 3D datasets. We found that Self-supervised 3D” / X
Robot Training
“How far are we from embodied intelligence? We first ask whether we can build a model to locate semantic concepts in 3D. Meet Find3D🔍: a model to locate any part of any 3D object based on any text query! 👉https://x.com/ziqi__ma/status/1859634303296266536





Leave a Reply