Edgar Bernal

Computer Scientist. Game Developer
UCV💻 + USB 🎮
🦔⚽

[Alexander Goslin @xandurglar]

Introducing InfiniteDiffusion, my independent paper accepted to #SIGGRAPH2026!

I have one RTX 3090 Ti. No funding, advisors, or team. By day I'm a new grad SWE at Walmart.

The paper has two main contributions:
- InfiniteDiffusion: a new approach to infinite generation with diffusion models.
- Terrain Diffusion: the world’s first learned procedural terrain generator.

Here’s why this matters, and how they are connected. 🧵

[MrNeRF @janusch_patas]

Release: LichtFeld Studio v0.5.3 is out!

With 316 commits merged into master, this release is a huge step forward for LichtFeld Studio.

What's new in v0.5.3

• Vulkan viewer/rendering migration: New Vulkan viewport pipeline, pass graph, VkSplat renderer, Vulkan point-cloud renderer, 3DGUT/VkSplat support, improved alpha/depth composition, tighter CUDA/Vulkan interoperability, and device matching on multi-GPU systems.

• RAD + LOD workflow: Added RAD file export/import, RAD LOD viewer, Spark-style GPU LOD selection, GPU-driven page prefetching, a bounded VRAM pool, out-of-core PLY-to-RAD LOD conversion, and RAD import/export speedups of approximately 3–5×.

• HiGS / macro-tile inference: Added a macro-tile inference path for the Vulkan viewer, including macro sorting, batched rasterization, composition, and capacity management.

• Asset Manager: Added and significantly enhanced the Asset Manager with thumbnails, SH information, faster synchronization, import-from-URL support, docked mode, data-loading popup integration, and general UI cleanup.

• Viewport export: Integrated viewport export directly into the application as a toolbar/overlay tool, added fast render_view_u8-style readback paths, fixed high-resolution clipping issues, improved orthographic export parity, resolved 32K image/video export problems, and added post-export GPU resource cleanup.

• Selection and tooling: Added and reworked selection toolbar controls, the Select menu, ring selection, color eyedropper, distance-from-center selection, faster point-cloud and zoomed-out selection paths, Vulkan measurement tool fixes, and drag-and-drop scene graph improvements.

• UI/RmlUi platform work: Major RmlUi redesign efforts, hot reloading for RML/RCSS/Python UI files, reactive UI/store integration, viewport toolbar flyouts, improved histogram interactions, input settings enhancements, custom TRS gizmos, and numerous panel, tooltip, and localization fixes.

• Windowing and UX: Added borderless window support, title bar drag/maximize/restore behavior, work-area-aware maximize functionality, resize responsiveness and performance improvements, and DPI/UI scaling fixes.

• Training and data features: Added adaptive depth loss and depth gradients for the EWA rasterizer, mask loading/application fixes, a new combined Ignore+Segment mask mode, --add-splat, --freeze, improved checkpoint and training state handling, and training speed and VRAM optimizations.

• COLMAP/equirectangular support: Added SPHERICAL/equirectangular camera model support and canonical EQUIRECTANGULAR handling, along with fixes for undistortion and camera export.

This release will be available to all supporters as a Windows binary via https://t.co/mdGITFOGVQ approximately in about an hour.

At the same time, LichtFeld Studio remains committed to being free and open source under GPLv3 and can also be built directly from source.

Please consider supporting the ongoing development of LichtFeld Studio through a donation via the portal or the supporters page.

Thank you to everyone who supports this project financially, contributes code, reports bugs, provides datasets, helps with the website, and contributes in countless other ways.

A special thank you to our foundational sponsor Core11 and our Gold Sponsor Volinga, whose support has helped make the current state of the software possible. Thank you as well to every donor and to all of our new Bronze Sponsors.

Looking ahead to v0.6

For the next major release, work will focus primarily on stability and user experience. This includes improved cleanup workflows and the ability to modify training parameters while training is in progress. I would also like to introduce a native .licht project format that allows users to save and restore their complete editor state.

You can find links to our main sponsors below. Please also visit our website to discover all our Bronze Sponsors.

Hint: We do not yet have a Silver Sponsor or Platinum 😉

[Chris Morris @Rustledust77]

The shader now detects the camera projection and does slightly different calculations to ensure the water depth and edge foam work correctly in isometric mode!

This article was a huge help: https://t.co/fsxNYNNvUC

#gamedev

[Mykhailo Moroz @Michael_Moroz_]

Made a gaussian splat of a norwegian fjord from a youtube video using my tool slang-splat
(https://t.co/rpL6avfOME)
Really love how these places look. Turned out better than I expected from a yt vid. Photometric compensation helped a lot with floaters.

[MIT CSAIL @MIT_CSAIL]

9 distance measures in data science w/algorithms (v/@MaartenGr).

[SHE 👑♡ @SHEISONX__]

How to generate free electricity.

[Burak is back @gecersandin]

Gerçekten çok mantıklı

[CopyRebeldia @CopyRebeldia]

Hoy una industria entera dejó de tener sentido.

Un tío publicó en GitHub un repo que convierte cualquier foto en un mundo 3D explorable: meshes con físicas, splat del fondo, audio ambiente. Todo.

Una imagen entra. Un mundo sale. Cinco minutos.

La gente que se pasó diez años aprendiendo Blender lleva todo el día mirando esto en silencio.

Se llama image-blaster.

[Dmitry Karpukhin @skx_doom]

Proof of concept: Sky Occlusion via LPV extension.
Super low res and low detail, but temporally stable. Perhaps could be used instead of DFAO...

Gives more like a feeling of a shadow on a scene, than something detailed. SSAO could be still used for contact details or so 🤔

[AK @andkalysh]

I have been working on BIG update for my #UE5 cheap LPV plugin and believe me, it's tremendous.

Separate LPV volumes you can place directly in your levels. Static or dynamic your choice.

Planned:
🔜 Multiple volumes per level
🔜 Forward rendering support
🔜 DX11 & DX12 Support

As far as my research goes light bounces are not possible for low end hardware without RSM.

#UE5 #UnrealEngine #gamedev #indiedev

[jendrik illner @jendrikillner]

Graphics Programming weekly - Issue 440 - May 10th, 2026 https://t.co/vC36nBIWy7

[roket @roikets]

Simple backyard project

[Dmitry Karpukhin @skx_doom]

Continuing working on a "potato GI" option for #UE5

My "LPV GI" plugin just received a new update with improved visuals, bug fixing, and a huge performance optimizations!

[Dmitry Karpukhin @skx_doom]

Seems like in the upcoming UE 5.8 the "Screen Space Fog Scattering" feature will be an included effect in the engine.
So, here are first tests with all the standard settings.

1. SSFS
2. Built-in
3. Off (for reference)

[Untold Secrets @RealGemsfinder]

Technical Engineering

[Julian Goldie SEO @JulianGoldieSEO]

NotebookLM + Google Gemini FULL COURSE 3 HOURS (Build & Automate Anything)

[angel @angeldot_]

GOOGLE CREÓ LA MEJOR HERRAMIENTA DE ESTUDIO DEL MUNDO

Es gratis. Lleva meses disponible.

Y el 90% de la gente no la conoce.

Te doy 6 prompts de NotebookLM para aprender lo que sea en tiempo récord.

📌Guárdalo, te salvará en tu próximo examen

[Dmitry Karpukhin @skx_doom]

My "Light Propagation Volume" plugin for #UE5 is now featuring Cascades system! It adds much longer light bounce distances, than what could be previously seen in the UE4's LPV implementation.

Still some work to do, performance-wise as well :) But it's shaping up very nicely.

[Javi López ⛩️ @javilop]

⚡ EL FUTURO ES AHORA

"Cada píxel será generado, no renderizado"

Google DeepMind acaba de lanzar Genie 3, la primera versión de Genie que por fin está abierta para que la prueben los usuarios.

Mira las locuras ABSOLUTAS que está haciendo la gente 🧵

[Alex Goldring @SoftEngineer]

Was working on CSM (Cascaded Shadow Maps) blending.

My CSM implementation is a little unusual, I switch cascades as late as possible, using the highest available resolution cascade.

Most CSM implementations choose cascades based on view depth, the problem with that is - you waste a lot of high resolution shadow texels, in my experience easily upwards of 50%.

I figure - GPU already spent the effort to compute those shadow texels - why not use them, and get perceptually about 20-50% resolution increase in your shadows.

This is not new, and MJP showed this in his code too (see below). The problem is in blending, if you use cascade projection matrix for choosing a cascade - blending becomes non-trivial. So I spent a lot of time working on that, and finally cracked it. Video shows blending of 5 cascades, the blend margin is exaggerated for demonstration purposes and cascades are pushed to the near plane for the same reason.

The result is a perfect forward-only blend at the cost of a bit of ALU.

@MyNameIsMJP is pretty much an authority on the subject nowadays, and I found his amazing repo very useful in the past: https://t.co/CevHJo3ZJF