Creating an animated Gaussian head from a single image, Large Avatar Model (github.com/aigc3d/LAM), shows the potential. I merged my head with this popular meme and it looks decent. I tried to find the Gaussian sequence but didn't find any tho, just the rendered video...

This is such a crazy cool NPR style! 3D 'paintings' in Blender

Are you tired of the low quality of iPhone lidar scans? I am! And that is why we are bringing this cutting-edge iPhone lidar scan enhancement function into production! With the guidance of normal and depth, the geometry can now reach the next level! Showcases:

Let me share how the maps look like. Normal was estimated from the source image with StableNormal (github.com/Stable-X/Stabl…), and Refined Depth came from promptDA (github.com/DepthAnything/…) + Lidar Depth. If you pause the video, you will see the differences in depths.

BTW, StableAlbedo is coming soon, built on the same architecture as StableNormal v2. Still Apache-2 licensed and free for commercial use. We hope this could accelerates research and applications in portrait reconstruction and relighting! #StableX #portraitphotography #Avatar

FastMap: Revisiting Dense and Scalable Structure from Motion "FASTMAP, a redesigned SfM framework, achieves fast, high-accuracy dense structure from motion. On large scenes with thousands of images, FASTMAP is up to one to two orders of magnitude faster than GLOMAP and COLMAP.

【Apple Vision Proで新次元のARショッピング🚀】 次世代ARアプリ『ubiquitous_spatial shop』ベータ版をリリースしました！ 空間にリアルな3D商品が浮かび、高精度3Dスキャン技術（KIRI Engine - 3D Scanner App

有料だけど以前ブログ記事にも書いたこのKIRI Engine。 約1分の動画から作ってもらった３DGS to Meshが普通にベースとして使えちゃうクオリティ。 車の周りをぐるっと回る動画撮っておくだけであとからこれが作れるのはお手軽でスゴイ。

MAC-VO: Metrics-Aware Covariance for Learning-based Stereo Visual Odometry TL;DR: learning-based stereo; learned metrics-aware matching uncertainty for dual purposes: selecting keypoint and weighing the residual in pose graph optimization.

Ultimate render tip: Add blur, then more blur, then noise, then grunge followed by blur

Little update on our coming Blender addon: Render Arena - Addon and documentation is done! - Now: Tidying up small odds and ends like nice thumbnails etc - Current features: lights presets, camera animation presets, automated backgrounds, compositing controls and more! - Here's a

📢 Introducing GenSfM – a generic Structure-from-Motion pipeline built on COLMAP, with smooth, invertible, and universal calibration for diverse cameras — from pinhole to catadioptric! Thanks Yihan_Wang Viktor Larsson Marc Pollefeys for the great collaboration. 🔗 ivonne320.github.io/yihan.home/Gen…

A failed replication! Lol, when I see Apple's spatial scene on WWDC25, I try to guess how they make it and attempt to create a pipeline to achieve a similar result. I used DepthPro from Apple and used AdaMPI (github.com/yxuhan/AdaMPI) from my friend Yuxuan, but the result is not

Batch processing scans? Zbrush is great but the UI can sometimes slow down your flow. Here's a little script to automatically generate High, Mid and Low poly variations 😃

🚨 Open Source Bounty – $300 🚨 Help speed up Gaussian Splatting training by 50% and win $300 💸 We’re challenging the community to optimize CUDA training in our repo! ✅ Must preserve accuracy 🚫 No non-permissive licenses (don't reuse bad licensed code) 📜 Must include a

Thrilled to unveil LINO - Light of Normals! 🌟 We Achieve Up to 4K Resolution & 3D Scanner-Level Accurate Surface Normals Estimation. How? ☀️Learnable Light Register Tokens 🔬Preserve high-frequency details via Wavelet Sampling Try it at github.com/houyuanchen111… !