Neal

Developer of 📷 - Ai rendering engine for Blender and 3Ds Max.
💡 3D designer, emerging tech and innovation enthusiast

[Alex Orsholits@UTokyo @highvis_supply]

ZipDepth Vs DepthArt quick test

Only managed to get DepthArt rel S 448 to run properly on the Qualcomm NPU with little to no artefacts at the moment

[Qwen @Alibaba_Qwen]

🎨 Meet Qwen-Image-3.0 — the third generation of our foundational image generation model.

If 1.0 was about "Precision," and 2.0 added "Variety, Completeness, Beauty & Authenticity," then 3.0 comes down to a single word: Real (实).

Three dimensions of "Real":
📰 Rich Content — prompts up to 4.5k tokens. One-pass generation of complex layouts: newspapers, storyboards, exam papers — even a 3×3 infographic grid or picture-in-picture-in-picture UIs.
🔬 Authentic Details — text legible down to 10px, full LaTeX paper pages, pores, hair strands & near-photographic skin texture.
🌏 Deep Knowledge — native rendering in 12 languages, 100+ art styles, realistic UIs (web / games / livestreams), plus world knowledge & live web retrieval.

Not just "good-looking" — genuinely useful. Image generation as a real productivity tool for design, content, education & e-commerce.

Go create 🏃🎨

💬Qwen Chat: https://t.co/941HmITJ2W
📝Blog: https://t.co/5mnS4uI9Ar

[Black Forest Labs @bfl_ai]

Introducing FLUX 3.

One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style.

FLUX 3 Video is now available in early access (link below).

Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

[Min Choi @minchoi]

Google DeepMind just unveiled GenCeption.

This AI turns video into depth, segmentation, 3D keypoints, and searchable 4D worlds.

8 wild examples:

[Tom Dörr @tom_doerr]

Accelerates SAM 3D Body by 10.25x, enabling real-time full-body human mesh recovery at 65ms per frame.

https://t.co/RZGVE9fdmi

[DailyPapers @HuggingPapers]

ReChannel

A new way to extract depth, normals, matting, and segmentation from a single image using a frozen text-to-image DiT — with only 33K trainable parameters per task.

[Gabriele Romagnoli @GabRoXR]

This is Segment Anything for #GaussianSplatting running on the web... but it comes with a caveat.

This is SplatEdit, a powerful #3DGS editing software built on top of SuperSplat.

Last week, it added a segmentation selection feature powered by Segment Anything, running locally in the browser. Just upload a splat, click on the "mug" icon and select entire objects in the scene.

The problem is that everything after the object is also selected (as you can see in the video).

To fix that, just use the brush tool to subtract the unwanted portion of the scene (hold CTRL while brushing).

I feel we are getting closer and closer to having more editing control on these amazing fuzzy clouds 😉

[DailyPapers @HuggingPapers]

GenCeption from Google DeepMind

A single feed-forward vision model that matches specialist models on depth, surface normals, camera pose, keypoints & segmentation

[Tomoki Itamiya 板宮 朋基 @t_itamiya]

CT/MRI画像から3DCGを高速に作成できるKaloLumenの無料デモ版をご提供します。医療関係者・研究者で以下のスペックのPCを持つ方はお気軽にDMください。このソフトは教育・研究用途で診断・診療には使えません。 OS: Windows 11 Home or Pro
CPU: 12th Gen intel® Core™ i7-12700Hと同等以上
RAM: 16GB以上
GPU: NVIDIA® GeForce RTX™ 3050, VRAM 6 GBと同等以上

[Bao-Thinh Dinh @Bipowpow]

How to make Ghosting Effect using Blender Compositor.

Node setup below..

#blender #eevee #compositor #porsche911

[Neal @NealMenhinick]

@jaskirat Have you considered make a web version?

https://t.co/8lXI0s9Frn

[Sadao Tokuyama @tokufxug]

Ant Groupが空間認識に特化した視覚基盤モデル「LingBot-Vision」を発表。

独自の「境界中心」のアプローチを採用し、1B（10億パラメータ）のViTでありながら7倍以上大きな既存モデルを上回る性能を発揮。

Apacheライセンスでコード公開。

[Adina Yakup @AdinaYakup]

@robbyant_brain https://t.co/rfMDewangx

[Richard Palethorpe @jichiep]

Playing with getting trellis2cpp working e2e on my 16gb card. They recommend using 24gb, but depending on how long you are willing to wait, it appears to work even on 8gb. @rms80

[Neal @NealMenhinick]

@poellll please make this an interactive tape player. maybe not, that would be too cool

[ǝɥǝ⅄ @YeheLiu]

Cool data!
https://t.co/11IcdK9FJP runs in your browser
Just drag and drop your colmap dataset with 3dgs ply
You could also host data on Huggingface for free or using your private bucket.

[Alexandre Morgand @Almorgand]

"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation"

TL;DR: a minimalist pixel-space diffusion transformer predicts dense 3D point maps directly from a single image, removing the need for VAEs and hybrid architectures while producing sharper geometry.

[Francis Engelmann @FrancisEngelman]

We added bending and tapering to superquadric reconstruction / decomposition.
➡️ big step forward in reconstruction quality
Check out SuperFlex for compact & explicit 3D object/scene representations. @eccvconf #ECCV
More details: https://t.co/ZVaZQznVAL

[Haofei Xu @haofeixu]

Does 3D reconstruction have to be complex?

We answer this question with PointDiT (#ICML2026): a minimalist pixel-space Diffusion Transformer without bells and whistles.

We show that a plain ViT can estimate dense 3D point maps by operating directly on raw patches. No hybrid ViT+Conv architectures, no lossy VAEs, no complicated training losses. (1/5) 🧵👇

[Linoy Tsaban @linoy_tsaban]

Super cool new sun direction relighting LoRA for Flux Klein 🌞

> Had my agent build a ZeroGPU demo for it using our new space builder skill for LoRAs from huggingface/skills

https://t.co/rn5nz8bdJg