Creators need precise control for 3D generation. Learn how Cartwheel built “Pose Mode,” a feature using Gemini 2.5 Flash to give artists direct, iterative control over a character’s pose and camera angle. Using two models, Gemini 2.5 Flash and Gemini 2.5 Flash Image, avoided model training bias, enabling consistent character generation from any angle. Learn how they built it: https://goo.gle/4p03fGJ

A new AI tool called Marble builds 3D worlds from images and text prompts using Gaussian splats. You get a quick, reusable static scene for games and simulations, reducing GPU requirements. Marble supports up to eight images and blends graphics with language for more accessible 3D design. - How does Marble create 3D scenes from images and text? - What are Gaussian splats in 3D modeling? - Where does Marble fit within game development or robotics tools? #ai #artificialintelligence #ainews #CarolEstrano #aiavatar

FlashWorld revolutionizes 3D scene generation with its cutting-edge technology. By leveraging a groundbreaking 3D-oriented generative model, FlashWorld can swiftly produce high-quality 3D scenes at remarkable speeds, surpassing traditional methods by 10–100×. This innovative approach directly generates 3D Gaussian representations, prioritizing realism and coherence. Thanks to its dual-mode pre-training and cross-mode distillation techniques, FlashWorld harmonizes the capabilities of both 2D and 3D frameworks. The result is outstanding rendering precision, robust adaptability, and instantaneous 3D scene creation from any input. Experience the future of 3D world generation with FlashWorld's unparalleled efficiency and realism. Project: https://lnkd.in/gzjtYG6g GitHub: https://lnkd.in/gMzUc4dw Paper: https://lnkd.in/g43iqFhm

Here is the second preview of upcoming #Verge3D 4.11. For this update we prepared: ☞ major quality and usability upgrade for screen-space reflection/refraction ☞ a convenience switcher between modeling tools in Verge3D Ultimate ☞ extended support for sky rendering and exposure settings in Blender ☞ transparency improvements for 3ds Max and Maya ☞ updated demos and docs ☞ fixed bugs! Check it out: https://v3d.net/1d6f

🚀 PlayCanvas Engine v2.13.0 is live! This update delivers major enhancements for 3D Gaussian Splatting on the web - expanding both performance and creative flexibility. ✨ Highlights ✅ Streamed LOD system - dynamically load and manage massive splat datasets. 🎨 Splat shader effects framework - new base for reveal, hide, tint, and bloom effects. 🌍 Globally sorted splats - improved rendering quality and stability for large-scale scenes. Plus a long list of refinements across the engine - from shader customization and GPU optimizations to lighting and input fixes. 🔗 Full release notes: https://lnkd.in/eYYsB2ty 🎮 Live examples: https://lnkd.in/e2shW8ST Huge thanks to our amazing contributors and community for continuing to push what’s possible in real-time web graphics. #PlayCanvas #WebGPU #WebGL #3DGS #GaussianSplatting #Web3D #OpenSource #GameDev #RealtimeGraphics

🔊 **VOLUME WARNING** (Listen with headphones) It's been about seven months since I began the development of AudioTracer, a 2D room acoustics simulator built with C++ and the raylib library, and I’m excited to share my progress. The project began as an opportunity to learn and—out of curiosity—explore the capabilities of the “ray-tracing algorithm”. For those unfamiliar, the ray-tracing algorithm is an algorithm simulates light propagation in a physical environment by *tracing rays* of light from a source as it bounces around hits a camera lens. Ray-tracing is well-known for its photorealistic results and has advanced in both quality and efficiency, especially as the “path-tracing algorithm” was introduced around the 1980’s. I wanted to step into this area of Computer Graphics and see how I could expand upon it, so I thought “instead of tracing light, I’ll trace sound!” As sound and light can generally be represented by waves that bounce around into our heads, redesigning the algorithm to accommodate sound wasn’t too difficult. As it is, the software is able to load and visualize 2D scenes including a listener (the green circle), from where the user will hear noises, sound sources (the yellow circle) from where sound sources originate, and walls (white lines), off which the sounds will bounce. This scene below features a floor plan created with my LineDrawer program and contains 2 sound sources, one within the “building” and one following the user (in green). The source in the building plays a bottle-breaking noise, and the user plays a snapping noise. The visualizer also features rendering metrics, as well as a histogram running along a radian axis, representing the volume of noises being rendered along different angles. For example, the middle of the histogram (~3.14 radians) represents sounds on the left side of your ear. Development proceeds as I continue to explore optimizations for the ray-tracing algorithm. I hope to add more sampling configurations, and optimize the algorithm, perhaps using BVH or CUDA parallelization. Keep up with development on AudioTracer’s GitHub repository:  https://lnkd.in/g7WsehxK #raytracing #computergraphics #computerscience #projects #raylib #rendering #simulation

The wildest demo on Hugging Face currently is this "Camera Control" LoRa trained on Qwen Image Edit 🤯 It lets you upload an image and generate a new scene by rotating the camera view. You can pan left/right, move forward or zoom in, and switch between bird’s-eye and worm’s-eye perspectives - all with just a few clicks. In other words, it adds full camera angle control to an image editing model, something Google's Nano Banana does not have. LoRA (Low-Rank Adaptation) is a technique for training only a few parameters on top of a frozen pre-trained model - in this case, Qwen Image Edit. This enables users to personalize models or add specific capabilities like camera control without retraining the entire model. The Space also leverages a variant called Rapid-AIO, which significantly speeds up inference, delivering great results in just four steps. Below someone tried it out on the "distracted boyfriend" meme, pretty cool right? Try it out here: https://lnkd.in/et3Yheug Source: https://lnkd.in/eaTZzHPr

The wildest demo on Hugging Face currently is this "Camera Control" LoRa trained on Qwen Image Edit 🤯 It lets you upload an image and generate a new scene by rotating the camera view. You can pan left/right, move forward or zoom in, and switch between bird’s-eye and worm’s-eye perspectives - all with just a few clicks. In other words, it adds full camera angle control to an image editing model, something Google's Nano Banana does not have. LoRA (Low-Rank Adaptation) is a technique for training only a few parameters on top of a frozen pre-trained model - in this case, Qwen Image Edit. This enables users to personalize models or add specific capabilities like camera control without retraining the entire model. The Space also leverages a variant called Rapid-AIO, which significantly speeds up inference, delivering great results in just four steps. Below someone tried it out on the "distracted boyfriend" meme, pretty cool right? Try it out here: https://lnkd.in/et3Yheug Source: https://lnkd.in/eaTZzHPr

This is what I miss sometimes in the discussions on AI: people lamenting on the accuracy of results produced by ChatGPT ("it's hallucinating all the time, the hype is not warranted") and missing the bigger picture of generative AI. The progress on signal processing and generation is super impressive and the easily available tools are often already "good enough" to replace a good amount of human work. As an example: of course you can pay a professional speaker to dub videos. Truth is: AI voice-overs might still lack the last 10% of authenticity and human touch to make same on par with a really good professional, but for most people it is just good enough and not worth it to pay more. Same will be for generating royalties-free background music, translations of documents etc. Of course this is not positive for the artists and professionals in these fields, but we won't be able to turn back time. We are living in very interesting times.