Spark 2.0 is an open‑source WebGL2‑based rendering engine that uses continuous LoD trees, a custom RAD file format, and GPU memory virtualization to stream and display massive 3D Gaussian‑splatting scenes on phones, tablets and browsers with smooth, real‑time interaction.
The article examines Peter Tarka’s 2025‑2026 3D renders—crafted in Cinema 4D with Octane—highlighting his extreme material realism, strategic high‑saturation color gradients, photographic lighting techniques, and surreal minimalist styling, while assessing the commercial appeal and potential coldness of this hyper‑polished visual language.
This guide walks creators through the complete workflow of generating realistic AI‑driven human scenes and converting them into 3D‑style visuals, covering style definition, tool‑assisted pipelines with Doubao and Stable Diffusion, LoRA training, and flexible weight blending for diverse artistic outcomes.
The MTSC 2024 Shanghai conference gathered top testing experts to discuss AI‑driven testing, full‑chain 3D rendering ecosystems, UI automation for graphics software, and front‑end performance assurance, offering a comprehensive look at emerging quality‑assurance practices and future collaborations.
The article details JD.Vision's development for Apple Vision Pro, explaining how spatial computing enables immersive 1:1 product placement, describing low‑latency VST, eye‑tracking hand‑eye control, custom gesture recognition using AI models, shader customization, and performance optimizations for a seamless AR shopping experience.
This article explores how JD.Vision, one of the first native apps on Apple Vision Pro, uses spatial computing, custom gestures, shaders, and performance optimizations to deliver a 3D immersive shopping experience that lets users place and interact with virtual products in their real environment.
This tutorial demonstrates how to use Three.js, TypeScript and Vite to load an SVG logo, extract its Bézier curve points, generate evenly spaced laser paths, animate multiple lasers with Line2, and finally separate the logo from a floor using shape holes, providing complete source code and visual results.
The article explains how Ant Group’s Galacean engine enables millions of participants to become digital torchbearers for the Asian Games by leveraging Web3D, physics‑based rendering, low‑code animation tools, and extensive cross‑device testing to create a scalable, interactive 3D experience.
This article explores how Stable Diffusion can revolutionize visual design by instantly converting line sketches into 3D scenes, turning flat cartoon IPs into detailed 3D characters, and generating creative font styles, while detailing the required models, ControlNet settings, prompts, and post‑processing techniques.
The article introduces core 3D rendering concepts, tracing the evolution from desktop OpenGL to mobile OpenGL ES and its JavaScript counterpart WebGL, explains GLSL shader programming, reviews common model formats like OBJ and FBX, highlights front‑end engines such as Three.js, compares rasterization with ray tracing, and mentions modeling tools and emerging AI‑driven techniques.
This article presents the Music XR Maker framework and its four core components—music-driven system architecture, dance generation, lip-sync driven by singing voice, and expressive singing facial animation—detailing data sources, AI generation pipelines, 3D rendering, product applications, and future research directions.
The article details how Taobao Life’s “Life Cabin” feature was built using the in‑house Hilo3D WebGL engine, describing a pipeline that converts Maya‑exported USD models to GLTF, sets up cameras and controls, manages avatar movement, implements interactive furniture logic, and applies shadow‑map and baked‑light optimizations for smooth performance.
An end‑to‑end pipeline is presented that uses Blender to split and UV‑map a frame model, exports it as FBX, imports it into Unity where a runtime API dynamically updates materials, textures, colors and shininess for digital collectibles in the Taobao app, addressing mesh processing, FOV, lighting and anisotropic filtering issues.
This article guides beginners through the fundamentals of computer graphics, explaining OpenGL, WebGL, GLSL, and the rendering pipeline, then demonstrates practical Three.js code for setting up scenes, cameras, lights, materials, and textures to create interactive 3D web experiences.
This article details the end‑to‑end design and implementation of a 3D immersive food‑shopping experience, covering project goals, architecture split between Babylon 3D rendering and DOM rendering, resource management, camera collision handling, map integration, performance optimizations, and lessons learned.
The article surveys digital‑human technology—covering visual form, motion and AI‑driven intelligence—its fast‑growing market, a three‑layer solution stack (hardware/software base, AI platform, application services), end‑to‑end avatar creation workflow, rendering and animation techniques, web‑deployment challenges, and future prospects such as deeper AI, XR/6G and metaverse integration.
This article explains the adaptive 3D face cutout technology behind Kuaishou's "3D Zoom Face" effect, detailing its problem‑solving approach, implementation workflow, camera‑control optimizations, and how it expands creative possibilities while lowering production costs for both creators and users.
This article, originally presented at the 16th D2 Front‑End Technology Forum, explores the current state, market potential, and core technologies behind virtual digital humans—covering their appearance, behavior, and intelligence—while detailing practical pipelines, rendering techniques, and future challenges for web‑based implementations.
This article introduces the essential concepts and step‑by‑step implementation of 2D and 3D graphics rendering on the web, covering viewport transformation, triangle rasterization, anti‑aliasing, interpolation, camera setup, perspective projection, and depth testing using HTML5 Canvas and JavaScript.
This article defines virtual characters, traces their origins from the 1989 Visible Human Project to modern digital idols, examines market growth across e‑commerce, finance, film and gaming, outlines the industry’s three‑layer architecture, showcases leading products and solutions, and details the technical research areas such as 3D art pipelines, facial‑animation, rendering, scene orchestration, and big‑data‑driven algorithms pursued by Alibaba’s front‑end team.
The article analyzes how GPU architecture, originally designed for 3D graphics, is being reshaped by AI demands through specific‑domain designs, hardware/software interfaces, tensor acceleration, and 3D/AI convergence, ultimately arguing that GPUs will remain the central compute platform in the new golden age of computer architecture.
This tutorial walks you through the complete workflow for producing photorealistic interior visualizations, covering floor‑plan acquisition, 3D modeling, material setup, lighting, rendering settings, and post‑processing using 3ds Max and Vray.
This article presents a method for fine‑grained control of highlight effects in 3D material makeup by analyzing lighting models, material parameters, and geometry, and proposes using model‑space normal maps to achieve stable, adjustable highlights that meet aesthetic requirements.
This article presents a method for fine‑grained control of highlight effects in 3D material makeup, analyzing the impact of material properties, lighting, and geometry, and proposes using model‑space normal maps to ensure stable, adjustable highlights across different facial models and poses.
This article examines the challenges faced by Chinese SMEs in apparel design, surveys leading 3D clothing tools such as Marvelous Designer, CLO3D, and Style3D, analyzes cloth simulation algorithms, and presents a Three.js‑based demo enabling web‑based 3D rendering with fabric swapping and decal addition.
The Eagle.gl Web 3D engine, built atop Three.js, provides a unified 2D/3D GIS platform that efficiently loads, renders, and edits massive point‑cloud, vector, and model map data with real‑time LOD, GPU picking, DEM terrain integration, and configurable styling, supporting AMap’s HD‑map production and future autonomous‑driving simulation.
This article explains how Kuaishou's audio‑video team implemented panorama video technology in 2020, covering its historical background, user impact, data analysis of a viral video, and the technical pipeline that creates a spherical model, projects it, and renders immersive 360° playback on mobile devices.
The article guides front‑end developers from basic 2D charting to immersive 3D data visualizations, explaining WebGL’s rendering pipeline, comparing libraries such as Three.js and Babylon.js, detailing camera, lighting, model handling techniques, and showing how Draco compression dramatically shrinks GLB assets while preserving quality.
This article traces the evolution of computer graphics in video games—from the 1972 Brown Box and Atari sprites through the ZX Spectrum era, early 3D engines like Freescape and Zarch, to the rise of GPUs, rasterization pipelines, and modern rendering challenges exemplified by titles such as Crysis.
This article details the technical implementation of Ant Group’s annual Five Blessings Spring promotion, covering the business breakdown, 3D scene construction using the Oasis engine, sliding control logic, visual effects, and extensive performance optimizations for memory, texture, buffers, and loading on mobile web.
The article explains how AMap JSAPI 2.0 achieves realistic 3‑D building lighting by applying the Blinn‑Phong model with ambient, diffuse and specular components, employing directional, point and spot lights together with a classic three‑point lighting setup—including a high‑altitude point light over the Oriental Pearl Tower—to produce depth‑rich, non‑flat visualizations.
Didi’s Navigation system combines a novel MJO 3D panoramic map with advanced data‑compression and octree rendering, precise main/sub‑road yaw detection using LSTM‑based models trained on GPS and image data, and a lightweight deep‑learning engine optimized for mobile CPUs/GPUs, delivering accurate, real‑time guidance for ride‑hailing and autonomous driving.
The article introduces SpriteJS's new 3D extension built on the lightweight OGL library, compares it with popular 3D engines, explains its DOM‑friendly API, and provides extensive code examples for creating cubes, meshes, lighting, shadows, video textures, panoramic scenes, and advanced effects such as render targets and GPGPU, demonstrating high performance and ease of use for front‑end developers.
The article presents a comprehensive overview of the 3D rendering pipeline used to build a virtual avatar system for live streaming, covering layered rendering, mesh swapping, bone deformation, HSV‑based coloring, depth handling, transparency, shadow methods, and physically‑based lighting to achieve high‑quality interactive visuals.
This article presents Huajiao's 3D rendering system for live streaming, covering multi‑layered rendering, avatar outfit and accessory swapping, bone‑based shape editing, HSV‑based color tinting, depth handling, transparent hair rendering, shadow techniques, and physically‑based lighting to achieve high‑quality, interactive virtual avatars on mobile devices.
Ant Financial’s Oasis 3D engine, a lightweight, component‑based WebGL solution, enables efficient real‑time 3D rendering on browsers and mobile devices, offering features such as scene graphs, PBR support, animation systems, and an online editor that streamlines the entire 3D development workflow.
This article explains how to use WebGL and the Three.js library to create a cross‑platform 3D medal system, covering model format choices, scene setup, rendering code, performance optimizations such as gzip compression, caching, skin switching, and graceful fallback for older devices.
At the Global Front‑End Technology Conference, Amap’s senior expert Wang Qianwei will present “Practical Engineering of 3D Map Rendering Based on GLES,” discussing mobile and automotive rendering challenges, cross‑platform architecture, data compression, OpenGL performance tuning, fast‑iteration toolchains, and future Metal and Vulkan graphics directions.
This article examines the evolution of smart terminals, outlines the sensor and computing trends driving new mobile experiences, and details Alibaba’s xMedia SDK—including its rich‑media foundation, on‑device deep‑learning engine (xNN), SLAM positioning (xSLAM), 3D rendering (xAnt3D), and cross‑platform capabilities—showcasing how these technologies enable more intelligent, decentralized user interactions.
This tutorial walks through using Three.js to create basic 3D scenes in HTML, covering library inclusion, renderer, scene, camera, object creation, camera positioning and angle adjustments, as well as adding rotation effects and rendering textured objects, with visual demos and code snippets.
Tmall’s 618 festival showcased cutting‑edge AR, 3D interaction and cross‑screen experiences built on the TidaSDK, Interactive Alliance, Hailuo Dock platform and the Hilo3D engine, illustrating how a unified SDK and optimized web rendering enable immersive e‑commerce innovations.
