Cristian Domínguez Rein-Loring

Emmy winner | Tech lead @RealityLabs | Building Agentic AI systems | Passionate about the future of entertainment | Spaniard in Los Angeles | Dog dad

[Cristian Domínguez Rein-Loring @Kripstian]

I have worked with tentpole artists to broadcast their music live in virtual reality for the last few years, but I don't post much about it.

Here's a thread with some of the shows I'm most proud of 🧵🔽

[Cristian Domínguez Rein-Loring @Kripstian]

@dotconor @KarolBuilds @steipete @pashmerepat @dotconor I’d be interested to collaborate on your 3D slide restoration idea, been working on similar stuff

[Cristian Domínguez Rein-Loring @Kripstian]

Hello world.

[Matthias Niessner @MattNiessner]

📢GaussianGPT: autoregressive 3D Gaussian scene generation.

We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline.

Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis.

🌐 https://t.co/Ewv4CyLD2O
▶️ https://t.co/zKOugfD9gl

Great work by @nicolasvluetzow, @barbara_roessle, @katha_schmid

[Cristian Domínguez Rein-Loring @Kripstian]

@unicornioenparo @JaimeObregon Yo me he tenido que montar esto para dejar de pegarme con el buscador del Petete... https://t.co/spl6cqIvV0

[Cristian Domínguez Rein-Loring @Kripstian]

I grew up in Spain hearing: you don’t need to know everything, just who to call. America felt more like: go figure it out yourself. AI is changing that. When answers become abundant, the real advantage shifts to judgment, taste, and execution.

[Cristian Domínguez Rein-Loring @Kripstian]

Attended an OpenClaw meetup in Koreatown this weekend. The energy in the room reminded me of my first trips to Silicon Valley ten years ago; a bunch of people building things that don't fully exist yet, sharing setups, genuinely excited. Haven't felt that in a while.

[Cristian Domínguez Rein-Loring @Kripstian]

Been playing with Openclaw for the last three days. This rabbit hole has no end. On the other side, there's only a beginning.

[Cristian Domínguez Rein-Loring @Kripstian]

@razib_ul47671 Free

[Cristian Domínguez Rein-Loring @Kripstian]

@felixhhaas Directory

[FLORA © @floraai]

With Nano Banana, your product campaign is ready in minutes.

Here’s a step by step guide:

1. Drop an image for style reference.

Analyze and extract the style by GPT-5.

[willie @ReflctWillie]

Reflct just came out of beta.
A polished, performant 3D Gaussian Splatting viewer that passes the 'Mom-test'.
Built for creators who want full creative control over how their splats are seen. Now powered by @playcanvas.

[Cristian Domínguez Rein-Loring @Kripstian]

@Jacobsklug @lovable Build

[Niantic Spatial 🌎 @NianticSpatial]

🚀 Niantic Spatial SDK v3.15 now supports @MetaQuestVR 3 via the new Passthrough Camera API—bringing advanced AR capabilities like meshing, semantics, and VPS to one of the most accessible mixed reality headsets.

🛠️ Try it now at https://t.co/HfqFUUm364 to set-up the SDK and explore sample projects. Give us feedback via [email protected] or our developer forum.

🔗 https://t.co/APx9IbwVf6

#SpatialComputing #NianticSpatial #MetaQuest3 #AR #VPS #ComputerVision #DeveloperTools #MixedReality

[Alexandre Morgand @Almorgand]

"Cameras as Relative Positional Encoding"
TLDR: comparison for conditioning transformers on cameras: token-level raymap, attention-level relative pose encodings, a (new) relative encoding Projective Positional Encoding -> camera frustums, (int|ext)insics for relative pos encoding

[4DVIEWS @4dviews]

We’ve been quietly working on a new way to visualise reality...

See you at @siggraph Vancouver from 12th to 14th August.

Come find us at Booth 417 for the full reveal. We'd love to show you what we've been working on.

#volumetricvideo #SIGGRAPH2025 #4Dviews #innovation

[Will Eastcott @willeastcott]

Some awesome humans scans from @ArtsReferences uploaded to SuperSplat! 🔥

[MrNeRF @janusch_patas]

SPaGS: Fast and Accurate 3D Gaussian Splatting for Spherical Panoramas

Contributions:
- We propose a novel spherical panoramic view-based free-viewpoint rendering approach using omnidirectional ray-splat intersection, facilitating precise 3D scene reconstruction with 360° panoramic images.

- Furthermore, we employ a novel tangent plane-based splat-bounding-box projection from camera space onto the equirectangular image plane to achieve substantial acceleration of the rasterization process. Additionally, we conducted a mathematical and geometrical analysis to ascertain its validity.

- We construct the first dataset for novel view synthesis using a drone, named Roaming and Rounding (RaR), encompassing ten scenes that collectively comprise perspective images and 360° panoramic images.

[Alexandre Devaux @AlexandreDevaux]

Turn any video into a 3D hologram ✨
Excited to share a working prototype that explores this, making standard videos feel more organic in WebXR. By leveraging video depth data, we can bring them to life as interactive particle clouds.
Demo: https://t.co/K4AqHKONdb
#XR

[Gabriele Romagnoli @GabRoXR]

These are displays that mimic how the human eyes truly see 👁️

The Swiss startup that makes them recently raised 8.9M and I had the chance to talk with the founder, Tomas Sluka, some time ago to understand what it takes to make wearable AR devices a reality.

Here is the full interview 👉 https://t.co/DkdmHjGI10

[SkalskiP @skalskip92]

VLMs are getting a lot better at detection and segmentation

with supervision-0.26.0 we shipped more tools allowing you to parse and visualize results from top VLMs

links to demos end examples below

link: https://t.co/xXMRaS3Guk