Procedural Gaussian Splats in PlayCanvas 🔥 Everything becomes splats:... Images. Text. Lines. One unified render, seamlessly blending with 3DGS models.show more

🔥Happy New Year all! 🧨 In 2026 Splats will... be like pixels! Ultra dense 3D Gaussian Splatting VFX Backdrops! In 360° → 3DGS pipeline >8M splats per scene Zero compromises on detail! Every surface. Every edge. Every reflection. This is what photorealism should look like:-) #GaussianSplatting #unity3d #GameDev #VR #3DGS #Physics #madewithunityshow more

Re-lighting Gaussian Splats in PCVR /Quest3 has finally full... support In Splatbox.📷 Grab it now: The SplatBox major update is here: Full PCVR Support: + standalone XR support (Quest 3 ready) 60+ FPS with 4M+ splats running live in VR(PCVR) Proper stereo rendering in Multi-Pass (no more warping) Tilt-Shift effect now works in VR Demo scene included Tons of fixes & quality-of-life upgrades Edit, relight, and render 3DGS scenes inside your headset. #GaussianSplatting #3DGS #VR #Quest3 #Unity #Unity3D #PCVR #XR #SplatBoxshow more

This is the first Gaussian splat I ever created... - a self-portrait from Nov 2023 scanned with Luma. The PlayCanvas Engine has come so far in the last 2+ years. SuperSplat can now stream splats of unlimited size with precise collision and crazy performance. Free and open source. 🚀show more

3DGS needs to fix this if they want to... be used for virtual tours: Gaussian splats struggle with ceilings. NeRFs ALWAYS beat out quality in this respect. I captured this over the weekend to compare. I have ideas on how to fix it. Anyone else have success with ceilings?show more

Today I am experimenting with visionOS 27’s native Gaussian... Splat Rendering It’s limited to 200,000 splats, BUT due to this, you can render them in shared space Zmienny helped train a rough test scan of my Rem figurine that I could place right next to the real one. Awesomeshow more

EDGS: Eliminating Densification for Efficient Convergence of 3DGS Contributions:... • We show that initial triangulation based on 2D correspondences can replace the incremental refinement process, fundamentally changing how 3DGS models allocate resources. • Our method reduces the path each Gaussian must travel in parameter space. Careful initialization not only accelerates convergence but also guides optimization toward a convergence point corresponding to lower reconstruction error and thus higher reconstruction quality. • Our approach outperforms both speed-optimized and quality-focused state-of-the-art models while using only half the splats of standard 3DGS. By improving initialization rather than altering the optimization process, this method is compatible with other 3DGS acceleration techniques, making it a flexible enhancement to existing models.show more

🧊 Splats → Voxels: Bridging 3D Gaussian Splatting with... Dynamic Voxels World Labs Just added this last tool to the GS editor plug-in that can convert any 3DGS splats into interactive voxel worlds with full physics support! 🚀 3 Rendering Modes: 🔵 CPU Mode - GameObjects for each voxel. Max physics interaction, perfect for destructible environments 🟢 GPU Mode - DrawMeshInstancedIndirect. Renders 100K+ voxels at 90fps. Pure visual, no physics overhead 🟡 Hybrid Mode - Best of both! GPU renders distant voxels Building this so you can literally punch through a GS World and watch it crumble 🥊 #GaussianSplatting #unity3d #GameDev #VR #3DGS #Voxels #Physics #madewithunityshow more

What happens when you reconstruct one of the world’s... most challenging landscapes? 🏆 #SplatYourWorld winner Hiroto Otsubo captured Salar de Uyuni with an Insta360 X5, processed in Scaniverse. Few landmarks, low texture, and extreme reflections make estimating depth & geometry difficult. Niantic Spatial’s reconstruction technology uses AI priors to help infer structure where visual features are sparse or ambiguous, producing higher-quality Gaussian splats with accurate geometry, scale & georeferencing. The result: machine-readable 3D models built for physical AI. Learn more: #GaussianSplats #SpatialAI #PhysicalAI #3DGS #3DReconstruction #AI #ComputerVisionshow more

Experimenting with using gaussian splats to create VR worlds... where people can watch my video in full 3D It's also for socializing and taking selfies in the locations that I record each video (or see the things that I show off) This is one part of my "XR Travel Vlogging" idea..show more

The (Processing) Level Required to Be Super We’ve had... clients ask us whether our 3D/4DGS capture and processing pipeline holds up in high-end VFX cinematic shots. Last year we were fortunate to work on the Superman production with Framestore (capturing Superman’s parents for a hologram), with our work shown on IMAX screens ~30 m high—so we’re confident the quality delivers. For this R&D preview, we ran test captures using an affordable off-the-shelf temporal plugin to reduce flicker and improve stability over time. We recorded @ 48fps from our 196x machine vision cameras and trained the 4DGS using Postshot at Ultra quality ~20 million splat resolution. What you’re seeing are stop-motion 3DGS frames. Each frame is an individual Gaussian Splat—processed to ~20 million splats for the full scene, then cropped and cleaned to ~6 million splats per frame. Our system—and the 3DGS process—picks up fine details like stray fine hairs, skin pores and woven cloth threads. Thanks for watching & stay super! Learn more @ #3DGS #4DGS #VFX #GaussianSplatting #IMAX #VolumetricCapture #Superman 4K Version here -show more

Excited to welcome Apple to Hugging Face Enterprise! 😍... Just yesterday Apple released Sharp - an amazing new model to turn images into 3D splats. Wonder how your iPhone magically turns your picture into moving images when you tilt it? With Sharp you can create this type of effect and more. With HF Enterprise, Apple will be able to publish technical articles on the HF blog - I for one would love to learn more about Sharp and the 150+ models, datasets and applications shared on HF!show more

Competition 2: Mesh Generation 🦾 Until now, our subnet... has focused on Gaussian splats. That work led to integrations with Unity, building the world’s largest 3D dataset, and early application deployments with real users and organic traffic growth. 🕹️ The next step is clear. Developers want native mesh generation that drops straight into existing game pipelines and unlocks real production use today. 🤖 Our competition format lets us move flexibly between goals, optimizing for near term commercial utility with meshes and balancing longer term research with Gaussian splat world models and digital twins. 📈 With significant open source mesh models releasing in the past weeks, the timing is right and the bar for miner innovation has never been higher. Mesh competition launches in 2 weeks!show more

Native image generation with Gemini is live 🚀🔥 You... can generate interleaved text and images and edit uploaded images all in a unified model. Big congrats to Robert Riachi Kaushik Shivakumar Fabian Mentzer and many more amazing folks who built this! Try it out and tell us what you think:show more

Create a 3D model from a single image, set... of images or a text prompt in < 1 minute 😮‍💨 This new AI paper called CAT3D shows us that it’ll keep getting easier to produce 3D models from 2D images — whether it’s a sparser real world 3D scan (a few photos instead of hundreds) or your favorite 2D image generator like Midjourney (just an image). How does this magic work? “This architecture is similar to video diffusion models, but with camera pose embeddings for each image instead of time embeddings. The generated views are passed into a robust 3D reconstruction pipeline to create the 3D representation (Zip-NeRF or 3DGS)”show more

A preview of what's next, visualized with Rerun and... PlayCanvas supersplat ✨ (Also, feel free to send me a DM 📩; I’ll be in San Francisco from July 21–29, and I'm looking to meet like-minded folks!) I'm convinced that Gaussian Splats will be an integral part of any data engine as an underlying representation. So I've started putting together a repo that: 1. Given a single image, perform image outpainting 🖼️🖌️ 2. Estimate a monocular depth map on the outpainted image 📏 3. Train a Gaussian Splat initialized from the monocular depth 🎓✨ 4. Warp to new views, perform inpainting on the missing masks -> Train new splat 🔄🎨 This is going to be integrated into exo-egoforge, but I wanted to start with the simple single-image version before moving to a multi-video implementation There's some weirdness in the final rerun visualization, but the trained splat looks great 🎉! This is all based on the very cool VistaDream paper ( .github.io/) More on this next week!show more

New Llama.cpp UI is a blessing for the local... AI world 🌎 - Blazing fast, beautiful, and private (ofc) - Use 150,000+ GGUF models in a super slick UI - Drop in PDFs, images, or text documents - Branch and edit conversations anytime - Parallel chats and image processing - Math and code rendering - Constrained generation with JSON schema supported Easy setup + open-source + community-built 🔥show more

Dreamina Seedance 2.0 is Officially here! Dreamina Seedance 2.0,... ByteDance’s AI-powered creative platform, lets creators easily transform ideas into high-quality videos. You can now edit videos like images, using up to 4 reference modalities (video, image, audio, and text) with precise control over visual effects, camera movements, and more. Why is this revolutionary? - 🔥 One-Prompt Video Editing: Edit videos seamlessly as easily as editing images. - 🎬 Multimodal Creativity: Combine images, video, audio, and text—up to 12 files at once. - 🎥 Remake Viral Content: Create high quality, professional-level videos with intelligent AI. - 🔧 Full Creative Control: Keep consistency in shots, typography, camera flow, and more. This isn’t just another video editing tool, it’s a one-stop AI workspace for all your creative needs. Ready to level up your content? Explore Dreamina Seedance 2.0 and start creating today. 🔗 #dreamina #seedance2 #seedream5 #dreaminatutorial #ai #aitools #aidesign #ecommercedesign #digitalmarketing #startupbusinessshow more

Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page:... Large text-to-image diffusion models have exhibited impressive proficiency in generating high-quality images. However, when applying these models to video domain, ensuring temporal consistency across video frames remains a formidable challenge. This paper proposes a novel zero-shot text-guided video-to-video translation framework to adapt image models to videos. The framework includes two parts: key frame translation and full video translation. The first part uses an adapted diffusion model to generate key frames, with hierarchical cross-frame constraints applied to enforce coherence in shapes, textures and colors. The second part propagates the key frames to other frames with temporal-aware patch matching and frame blending. Our framework achieves global style and local texture temporal consistency at a low cost (without re-training or optimization). The adaptation is compatible with existing image diffusion techniques, allowing our framework to take advantage of them, such as customizing a specific subject with LoRA, and introducing extra spatial guidance with ControlNet. Extensive experimental results demonstrate the effectiveness of our proposed framework over existing methods in rendering high-quality and temporally-coherent videos.show more

🔥 MiniMax H3 is now live on DomoAI. One... multimodal workflow. Multiple ways to create. ✍️ Text → Video 🖼️ Image → Video 🎵 Audio → Video 🎬 Video → Video With Omni Reference, combine up to 9 images, 3 videos, and 3 audio references in a single creation. More creative control. Less credits. 🚀Create with MiniMax H3 on DomoAI： #DomoAI #MiniMaxH3 #GenerativeAI #AIMusicVideoshow more

Throughout my journey in developing multimodal models, I’ve always... wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full support for parallelism and optimization. Not just to hack⚙️, but also to scale🚀. So finally we built it for ourselves. LMMs-Engine: a lean, efficient framework built to train unified multimodal model at scale. From Qwen LLM, VLM, LLaVA-OV, and WanVideo, to unified models like Qwen-Omni and BAGEL — plus Linear-Attn GDN and research prototypes like RAE and SiT - all under one modular system that seamlessly integrates diverse datasets and optimization strategies. Powered by FSDP2 multi-dim parallelism, Ulysses sequence parallel, Flash-Attention, Liger Kernels, and Native Sparse Attention (also with bonus support for the Muon optimizer for all models).show more