Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Classic 3D Rendering 古典的 3D レンダリング (Repost/Crosspost) #p5js #math #physics #code #art

kynd.info

7,096 subscribers

12,833 views • 1 year ago •via X (Twitter)

Arts #p5js #math #physics #code #art

Anya Rossi• Live Now

Private livecam show

2 Comments

貓頭鷹也是貓1 year ago

This animation is so well-done and easy to understand. Love it!

Digital Currency2 years ago

From 3D modeling to VR/AR development, our MSc in Metaverse program equips you with the technical skills to excel in the rapidly evolving digital world. Don't miss out—enroll today! #UNIC #MScMetaverse

Related Videos

Fluid Simulation 流体シミュレーション (Repost/Crosspost) #p5js #math #physics #code #art

Fluid Simulation 流体シミュレーション (Repost/Crosspost) #p5js #math #physics #code #art

kynd.info

19,391 views • 1 year ago

Fourier series : 3D Fourier machine Visualization |Animation | Interactive applet GeoGebra #geogebra #math #science #iteachmath #mtbos #visualization #elearning Bernat ANCOCHEA #physics

Fourier series : 3D Fourier machine Visualization |Animation | Interactive applet GeoGebra #geogebra #math #science #iteachmath #mtbos #visualization #elearning Bernat ANCOCHEA #physics

Daniel Mentrard

19,486 views • 7 months ago

$Math is beautiful. 🤓 Instantly make interactive fractal art with Gemini 2.5 Pro. Here’s a starter prompt: “Make me a beautiful particle based, animated, endless, 3D, symmetrical, fractal art piece inspired by a math formula.”$

Math is beautiful. 🤓 Instantly make interactive fractal art with Gemini 2.5 Pro. Here’s a starter prompt: “Make me a beautiful particle based, animated, endless, 3D, symmetrical, fractal art piece inspired by a math formula.”

Google

250,882 views • 1 year ago

I built a 3D engine in about a month. That wasn’t the original plan. Aperture began as research to test assumptions about WebGPU, ECS, 3D engines, and coding agents. It went further than expected: rendering, physics, examples, CLI, docs, showcase games. #WebGPU #AIAgents

I built a 3D engine in about a month. That wasn’t the original plan. Aperture began as research to test assumptions about WebGPU, ECS, 3D engines, and coding agents. It went further than expected: rendering, physics, examples, CLI, docs, showcase games. #WebGPU #AIAgents

Felix Z

25,752 views • 29 days ago

Integral Calculus StokesTheorem (Wouldn't this be a 3D extension of Green's theorem?) Visualization |Animation | Interactive applet GeoGebra #geogebra #math #science #iteachmath #mtbos #visualization #elearning Bernat ANCOCHEA #physics

Integral Calculus StokesTheorem (Wouldn't this be a 3D extension of Green's theorem?) Visualization |Animation | Interactive applet GeoGebra #geogebra #math #science #iteachmath #mtbos #visualization #elearning Bernat ANCOCHEA #physics

Daniel Mentrard

12,227 views • 1 year ago

new Sonic Project Hero build is really fun !! I think this is the most accurate we've ever gotten to proper classic Sonic physics in 3D

new Sonic Project Hero build is really fun !! I think this is the most accurate we've ever gotten to proper classic Sonic physics in 3D

Adri💫

124,005 views • 4 months ago

Introducing Texel Splatting: Perspective-Stable 3D Pixel Art open source paper+code Most 3D pixel art techniques (e.g. t3ssel8r, ProPixelizer) snap pixels to a screen grid, which only works with an orthographic camera Texel splatting solves this for perspective cameras: first,

Introducing Texel Splatting: Perspective-Stable 3D Pixel Art open source paper+code Most 3D pixel art techniques (e.g. t3ssel8r, ProPixelizer) snap pixels to a screen grid, which only works with an orthographic camera Texel splatting solves this for perspective cameras: first,

dylan

111,895 views • 4 months ago

Hermes studio：用AI玩了把古建筑3D化我给AI扔了张古建筑的参考图，它直接用Three.js生成了一座能旋转、能拆解，甚至能切换昼夜的3D古殿！

Hermes studio：用AI玩了把古建筑3D化我给AI扔了张古建筑的参考图，它直接用Three.js生成了一座能旋转、能拆解，甚至能切换昼夜的3D古殿！

libapi

16,793 views • 2 days ago

weekend hack: implicit.js an open source library that lets agents generate CAD with code + mathematical functions representing surfaces no CAD kernels, no STEP files just agents using math + code to directly generate 3D models details below!

weekend hack: implicit.js an open source library that lets agents generate CAD with code + mathematical functions representing surfaces no CAD kernels, no STEP files just agents using math + code to directly generate 3D models details below!

Jake Fitzgerald

34,761 views • 1 month ago

Compared MiniMax M3 against three other frontier open-source models: DeepSeek V4, Qwen 3.7 Max, and MiMo 2.5 Pro MiniMax M3 crashed others on: 1. collision physics 2. 3D pinball generation It was the only model that produced a result for the 3D pinball test For human motion rendering and hexagon sketching, Qwen 3.7 Max still tops

Compared MiniMax M3 against three other frontier open-source models: DeepSeek V4, Qwen 3.7 Max, and MiMo 2.5 Pro MiniMax M3 crashed others on: 1. collision physics 2. 3D pinball generation It was the only model that produced a result for the 3D pinball test For human motion rendering and hexagon sketching, Qwen 3.7 Max still tops

GMI Cloud

51,116 views • 1 month ago

🤖Simulation-Ready Human–Scene Interaction Reconstruction🤖 #HSImul3R reconstructs sim-ready 3D human-scene interactions from casual videos with *physics-in-the-loop* that can be directly deployed to humanoids. - Project: - Code:

🤖Simulation-Ready Human–Scene Interaction Reconstruction🤖 #HSImul3R reconstructs sim-ready 3D human-scene interactions from casual videos with physics-in-the-loop that can be directly deployed to humanoids. - Project: - Code:

Ziwei Liu

15,544 views • 4 months ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,708 views • 3 years ago

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

31,651 views • 4 months ago

🤔Is there such a thing as a 'cozy' coding game? In my game "Replicube" you replicate 3D objects made from cubes by writing simple code using math + logic. Available now on Steam (free demo too)

🤔Is there such a thing as a 'cozy' coding game? In my game "Replicube" you replicate 3D objects made from cubes by writing simple code using math + logic. Available now on Steam (free demo too)

Walaber

30,525 views • 1 year ago

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

Abdullah Hamdi

71,661 views • 1 year ago

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.

AK

38,571 views • 3 years ago

AAA is cooked. Genie 3 from prompt to game. Here's DOOM running near flawless (wait for it). This isn't 3D rendering it's not video. You control it. - Genie 3 is currently available for maxed plans. - They limit gameplay to about a minute. - Things have physics, NPCs react.

AAA is cooked. Genie 3 from prompt to game. Here's DOOM running near flawless (wait for it). This isn't 3D rendering it's not video. You control it. - Genie 3 is currently available for maxed plans. - They limit gameplay to about a minute. - Things have physics, NPCs react.

Grummz

64,110 views • 5 months ago

原稿用紙の中の2D世界と3Dの洋館を行き来するアクションゲーム『Chronoscript: The Endless End』2026年秋に配信決定新たなステージ「古代エジプト」やメインキャラクターのキービジュアルと3Dモデル、そして島崎麻里氏や光田康典氏といった参画クリエイター陣も発表

原稿用紙の中の2D世界と3Dの洋館を行き来するアクションゲーム『Chronoscript: The Endless End』2026年秋に配信決定新たなステージ「古代エジプト」やメインキャラクターのキービジュアルと3Dモデル、そして島崎麻里氏や光田康典氏といった参画クリエイター陣も発表

電ファミニコゲーマー

223,145 views • 1 month ago