Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Sparse allocation/rendering of SDF bricks is now working! The pipeline is fully GPU-driven - a series of compute shaders that manages brick allocation/baking in a 3D texture atlas, followed by draw-indirect for rendering. Still a lot more work to do, including automatic LOD.

miketuritzin's profile picture

Mike Turitzin

7,360 subscribers

39,001 görüntüleme • 1 yıl önce •via X (Twitter)

OyunBilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Another large speedup to SDF brick rendering (-20-40%) that is obvious in hindsight: When baking bricks, calculate the texel bounds that actually contain the surface, and then rasterize/ray-march just those bounds rather than the full brick bounds. 1/
0:17

Another large speedup to SDF brick rendering (-20-40%) that is obvious in hindsight: When baking bricks, calculate the texel bounds that actually contain the surface, and then rasterize/ray-march just those bounds rather than the full brick bounds. 1/

Mike Turitzin

11,310 görüntüleme • 1 yıl önce

Getting a bunch of questions about this! It's a full gpu rendering pipeline with built in shader editor for Rive, which can interleave 2D + 3D. Think WebGPU (minus compute, for now) that runs anywhere, not just the browser. You can implement anything at all. Cell shading. Background blurs. Deformation effects. And yes, even Rive vector components as textures. Shaders are precompiled and ship with your .riv. Minimal runtime size impact. Still WIP.
0:13

Getting a bunch of questions about this! It's a full gpu rendering pipeline with built in shader editor for Rive, which can interleave 2D + 3D. Think WebGPU (minus compute, for now) that runs anywhere, not just the browser. You can implement anything at all. Cell shading. Background blurs. Deformation effects. And yes, even Rive vector components as textures. Shaders are precompiled and ship with your .riv. Minimal runtime size impact. Still WIP.

Guido Rosso

22,034 görüntüleme • 2 ay önce

Redshift 2026.6 is out Check out the new features in Maxon's GPU renderer, including support for hex tiling to minimize visible repeats in texture maps #Redshift #Redshift3D #texturing #rendering #VFX #motiongraphics @maxonvfx
0:14

Redshift 2026.6 is out Check out the new features in Maxon's GPU renderer, including support for hex tiling to minimize visible repeats in texture maps #Redshift #Redshift3D #texturing #rendering #VFX #motiongraphics @maxonvfx

CG Channel

100,830 görüntüleme • 1 ay önce

Ran across this great article on sampled SDFs that has *great* interactive WebGL illustrations that work really well for building intuition on how this works. This technique works for SDF-based text rendering or baking of 3D geometry like in my project.
0:15

Ran across this great article on sampled SDFs that has *great* interactive WebGL illustrations that work really well for building intuition on how this works. This technique works for SDF-based text rendering or baking of 3D geometry like in my project.

Mike Turitzin

17,799 görüntüleme • 1 yıl önce

Realistic hair and fur rendering in EEVEE, is that of any interest to you as a 3d artist? 🤭 #b3d
0:14

Realistic hair and fur rendering in EEVEE, is that of any interest to you as a 3d artist? 🤭 #b3d

Gleb Alexandrov

17,787 görüntüleme • 8 ay önce

Bounded rendering in #ConjureSDF v0.3, a free update to support Blender 4.5+ Full release later this month. Speeds up rendering by only caring about pixels covered by the bounds of SDF groups. #blender3d #b3d #blender #3dart #3dmodeling
0:10

Bounded rendering in #ConjureSDF v0.3, a free update to support Blender 4.5+ Full release later this month. Speeds up rendering by only caring about pixels covered by the bounds of SDF groups. #blender3d #b3d #blender #3dart #3dmodeling

João Desager

13,704 görüntüleme • 8 ay önce

Stylized rendering Godot. More in the next update of Godot Shaders Bible 👉🏻 #GODOT #indiedev #gamedev
0:15

Stylized rendering Godot. More in the next update of Godot Shaders Bible 👉🏻 #GODOT #indiedev #gamedev

The Unity Shaders Bible

38,879 görüntüleme • 10 ay önce

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..
0:17

woww.. AI can literally do 3D rendering now just upload a draft 3D animation, it turns it into cinematic film scene you can control the looks of the car and environment with image refs no need days of rendering anymore..

el.cine

113,025 görüntüleme • 6 ay önce

Is Google taking initial steps to enhance Street View? For some reason, Street View seems stuck in technology that feels outdated. I wonder if we'll see such improvements on the product side. Also, note how much better it performs in all aspects compared to Zip-NeRF in their presented material. It offers more details and fewer artifacts. Great work! "LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering" Contributions: • We propose a novel LOD representation for 3DGS which, unlike previous methods [27, 28, 17], does not recompute the list of used Gaussians at each frame. This allows for acceleration and compaction, enabling the rendering of large-scale scenes even on mobile devices. • We design a strategy to automatically select optimal hyperparameters for splitting LODs, whereas most other methods require manual tuning of hyperparameters for each 3D scene. • To further accelerate rendering, we split the scene into chunks and pre-compute sets of active Gaussians per chunk. • Finally, we introduce a novel opacity interpolation scheme to produce visually pleasing rendering and eliminate artifacts when transitioning between chunks.
0:19

Is Google taking initial steps to enhance Street View? For some reason, Street View seems stuck in technology that feels outdated. I wonder if we'll see such improvements on the product side. Also, note how much better it performs in all aspects compared to Zip-NeRF in their presented material. It offers more details and fewer artifacts. Great work! "LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering" Contributions: • We propose a novel LOD representation for 3DGS which, unlike previous methods [27, 28, 17], does not recompute the list of used Gaussians at each frame. This allows for acceleration and compaction, enabling the rendering of large-scale scenes even on mobile devices. • We design a strategy to automatically select optimal hyperparameters for splitting LODs, whereas most other methods require manual tuning of hyperparameters for each 3D scene. • To further accelerate rendering, we split the scene into chunks and pre-compute sets of active Gaussians per chunk. • Finally, we introduce a novel opacity interpolation scheme to produce visually pleasing rendering and eliminate artifacts when transitioning between chunks.

MrNeRF

62,511 görüntüleme • 1 yıl önce

📺 VHS and CRT simulator for Unity. 🔴🟢🔵 Fully procedural (including RGB subpixel rendering) and blazing fast, though I'm not completely happy with the CRT stuff. Still a work in progress. #unity3d #gamedev #realtimevfx
0:14

📺 VHS and CRT simulator for Unity. 🔴🟢🔵 Fully procedural (including RGB subpixel rendering) and blazing fast, though I'm not completely happy with the CRT stuff. Still a work in progress. #unity3d #gamedev #realtimevfx

Mirza Beig

51,292 görüntüleme • 1 yıl önce

Hope in 3D! Still a lot of work to do! 💪💦 How do you feel about seeing work in progress posts? 🙇‍♂️
0:10

Hope in 3D! Still a lot of work to do! 💪💦 How do you feel about seeing work in progress posts? 🙇‍♂️

Scaredy_Hare

14,308 görüntüleme • 4 ay önce

Finally got something to show - we're working on a new 3D library for React Native! 👀🧊 👉 Powered by native Graphics APIs (Metal/Vulkan) 👉 Full control over rendering in JS 👉 120 FPS rendering on a Worklet Thread (no lags!) 👉 Supports hotswapping .glb/.gltf models
0:12

Finally got something to show - we're working on a new 3D library for React Native! 👀🧊 👉 Powered by native Graphics APIs (Metal/Vulkan) 👉 Full control over rendering in JS 👉 120 FPS rendering on a Worklet Thread (no lags!) 👉 Supports hotswapping .glb/.gltf models

Marc

86,147 görüntüleme • 2 yıl önce

#Blender 5.1 is here Read our pick of the 5 key features in the #opensource 3D software, from the new Raycast and Mask to SDF nodes to improvements to #rendering and #animation #B3D #3Dmodeling #texturing #gamedev #VFX #motiongraphics Blender 🔶
0:11

#Blender 5.1 is here Read our pick of the 5 key features in the #opensource 3D software, from the new Raycast and Mask to SDF nodes to improvements to #rendering and #animation #B3D #3Dmodeling #texturing #gamedev #VFX #motiongraphics Blender 🔶

CG Channel

32,106 görüntüleme • 3 ay önce

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩
0:15

Fun & likely unintended use case for #NanoBananaPro: image→3D point cloud Prompt: This is a rendering of a 3D model of a person. Make an accurate image of the corresponding normal map. Then I run Poisson-based normals→3D Pretty amazing for a general-purpose 2D image model 🤩

Keenan Crane

71,561 görüntüleme • 7 ay önce

What was a complex hacky pipeline in 2023 to take indoor 3d scans and reskin them to different types of decor is now just a few clicks in 2025. World labs marble has collapsed a lot of the complexity involved in generating and editing 3d worlds:
0:13

What was a complex hacky pipeline in 2023 to take indoor 3d scans and reskin them to different types of decor is now just a few clicks in 2025. World labs marble has collapsed a lot of the complexity involved in generating and editing 3d worlds:

Bilawal Sidhu

85,909 görüntüleme • 7 ay önce

Blender 4.3 is now available to download Read our pick of the 5 key new features in the #opensource 3D app, from Grease Pencil 3 to updates to #digitalsculpting, materials and #rendering, including light linking in #Eevee #B3D #gamedev #VFX @blender
0:15

Blender 4.3 is now available to download Read our pick of the 5 key new features in the #opensource 3D app, from Grease Pencil 3 to updates to #digitalsculpting, materials and #rendering, including light linking in #Eevee #B3D #gamedev #VFX @blender

CG Channel

43,281 görüntüleme • 1 yıl önce

⚛️ In React, rendering large lists or tables can be a drag on performance. The fix? Virtualization! the process of only rendering part of that large data set (just enough to fill the viewport). ✅ Improves rendering time significantly. ✅ Lowers memory consumption.
0:11

⚛️ In React, rendering large lists or tables can be a drag on performance. The fix? Virtualization! the process of only rendering part of that large data set (just enough to fill the viewport). ✅ Improves rendering time significantly. ✅ Lowers memory consumption.

George Moller

55,288 görüntüleme • 1 yıl önce

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:
0:12

Introducing Kaleido💮 from AI at Meta — a universal generative neural rendering engine for photorealistic, unified object and scene view synthesis. Kaleido is built on a simple but powerful design philosophy: 3D perception is a form of visual common sense. Following this idea, we formulate rendering purely as a sequence-to-sequence generation problem, successfully unifying neural rendering with the architecture principles behind modern language and video models. Unlike traditional neural rendering methods, Kaleido learns 3D purely in a data-driven way, without explicit 3D representations or structures. It acquires spatial understanding directly through large-scale video pretraining, then multi-view 3D data finetuning, inspired by how LLMs acquire textual common sense from large corpora before specialising in domains like coding. Through extensive ablations, we progressively modernised the architecture design and training strategies and tackled key scaling challenges in sequence-to-sequence generative rendering, arriving at a design that’s simple, versatile, and scalable. Kaleido significantly outperforms prior generative models in few-view settings, and remarkably is the first zero-shot generative method matches InstantNGP-level rendering quality in multi-view settings. We view Kaleido also as an alternative step towards world modeling that flexibly spans a spectrum of “realities": with many views, it faithfully reconstructs grounded reality; with fewer views, it imagines plausible unseen details. 🔗 Explore more results and paper:

Shikun Liu

22,134 görüntüleme • 8 ay önce

Virtual Community provides an online pipeline that automatically generates 3D scenes from real geospatial data, performing comprehensive cleaning and enhancement of both geometry and texture — including mesh simplification, texture refinement, object placement, and automatic annotation. 3/n
0:18

Virtual Community provides an online pipeline that automatically generates 3D scenes from real geospatial data, performing comprehensive cleaning and enhancement of both geometry and texture — including mesh simplification, texture refinement, object placement, and automatic annotation. 3/n

Chuang Gan

20,795 görüntüleme • 1 yıl önce

The ALTO Token Allocation Checker is now LIVE. Verify your token allocation here:
0:12

The ALTO Token Allocation Checker is now LIVE. Verify your token allocation here:

Alto

16,445 görüntüleme • 4 ay önce