The article analyzes three distinct architectural approaches for AI agents to control Blender—real-time MCP remote control, automated CLI harness generation, and visual feedback loops—comparing their trade-offs in interactivity, determinism, and quality assurance for 3D production workflows.
After GPT‑5.6 became fully open, the author tests its design power by presenting eleven diverse examples—from a voxel‑style Manhattan and Blender automation to city‑island scenes, a 3D globe dashboard, procedural terrain, a Google‑Earth clone, UI replication, Kyoto street view, a 3D watch, a GTA‑6 prototype, and a Xiaohongshu clone—highlighting cost, token usage, and quality improvements over previous versions.
Using GPT‑5.6 Sol, Codex, and Three.js, a solo developer transformed AI‑generated 2D organ sketches into an interactive 3D anatomy web app, compressing assets from 900 MB to 28.6 MB, adding on‑demand loading, and demonstrating how generative AI can lower the barrier to creating educational 3D content.
The article analyzes the limitations of traditional image‑to‑3D pipelines that output binary GLB files, introduces the open‑source img2threejs project that converts a single product image into editable Three.js TypeScript code with built‑in animation, version control, and quality checks, and provides detailed usage steps, comparisons, and practical constraints.
This article demonstrates a step‑by‑step workflow using the GenVizu AIGC platform, where an industrial designer starts with a simple 3D model, employs AI prompts and agents to generate high‑quality renderings, multi‑angle views, CMF mood boards, e‑commerce graphics, and even a concept video, dramatically speeding up the design output.
The article presents eleven striking GPT‑5.6 design examples—from a voxel‑style Manhattan and Blender‑driven scenes to city‑floating islands, a 3D globe dashboard, procedural terrain, a Google‑Earth clone, UI replica, Kyoto street view, a 3D watch, a GTA‑style world, and a Xiaohongshu clone—highlighting the model's design power, cost, token usage, and code size compared to earlier versions.
Tsinghua researchers propose a non‑overlapping RGB‑T adversarial clothing that uses printable fabric for visible‑light patterns and aluminum film for thermal patterns, achieving over 90% attack success in digital simulations and about 60% success in real‑world tests across multiple fusion detectors.
Pascal Editor is a free, open‑source, WebGPU‑accelerated online 3D architecture editor that runs in any modern browser, offering end‑to‑end space editing, high‑performance rendering, parametric tools, multi‑format export, a modular React‑based architecture, and use cases ranging from interior design to education, while outlining its strengths and current limitations.
This guide walks you through using Tripo Studio 1.0—from logging in and navigating its three‑pane workspace, to exploring a massive AI‑curated asset library, generating models via text or image prompts, and applying iterative optimization tools such as splitting, retopology, texturing and rigging for real‑world projects like games, 3D printing and product design.
FantasyWorld introduces a geometry‑enhanced framework that augments a frozen video diffusion model with a trainable geometry branch, enabling simultaneous video representation and implicit 3D field generation, achieving spatially consistent, high‑quality virtual worlds and outperforming recent baselines in multi‑view coherence and geometric fidelity.
This article reviews the latest open‑source AI models released by major tech firms—including Tencent's 3D‑Omni and 3D‑Part, Shengshu Tech's Vidu Q2 for facial video, Nvidia's Audio2Face for real‑time facial animation, plus updates from Figma, Google, Alibaba and Kuaishou—highlighting their capabilities and potential applications in gaming, AR/VR, design and content creation.
The article explains what digital humans are, reviews the evolution of 3D modeling techniques—from early 2D hand‑drawn methods and 3DMM to deep‑learning‑based implicit models like NeRF—and discusses current challenges and future research directions.
This article shows designers how to combine AI services such as Deepseek, JiMeng, Tripo, Tongyi and Jianying to accelerate 3D modeling, PPT creation and short‑video production, turning lengthy manual tasks into fast, creative processes.
This article presents a comprehensive technical guide on building a mixed‑reality hotel‑booking experience for Apple Vision Pro, covering background challenges, Vision Pro hardware and visionOS capabilities, ARKit and RealityKit integration, 3D modeling workflows, optimization techniques, interactivity implementation, and cross‑platform promotion strategies.
Over the past year JD Retail’s technology team has rolled out a suite of AI‑driven breakthroughs—from end‑to‑end inventory management and explainable AI in supply chain, to large‑language‑model frameworks, advanced advertising, edge‑AI, secure data platforms, and high‑quality 3D modeling—earning industry awards and boosting efficiency across e‑commerce.
In 2023 JD Retail’s technology team delivered a suite of AI‑powered innovations—including end‑to‑end inventory management, explainable AI for supply chain, privacy‑preserving advertising models, a ReAct‑SFT‑RAG large language model framework, edge AI inference, secure data‑safe‑house infrastructure, and high‑quality 3D modeling pipelines—demonstrating broad academic and industrial impact across multiple domains.
In 2023 JD Retail Technology showcased a series of AI‑powered innovations—including end‑to‑end inventory management, explainable AI for supply chain, large‑language‑model frameworks, edge‑device inference, data‑security "security house", and high‑quality 3D modeling—demonstrating how advanced algorithms and large‑scale computing boost efficiency, accuracy, and user experience across the e‑commerce ecosystem.
This article explores the concept of the metaverse and virtual humans, detailing 3D modeling techniques, NLP-driven language understanding, streaming TTS, VR/AR interaction, AIGC content generation, and the deployment of a large‑model intelligent Q&A system with real‑time facial expression synthesis for virtual anchors.
The article shows how the vivo front‑end team built a lightweight, mobile‑friendly 3D exhibition hall for the Game Festival by modeling in Blender, exporting GLB files, and using Three.js to set up the scene, lighting, shadows, joystick navigation, collision detection, and performance optimizations such as texture baking and model compression.
This comprehensive guide walks through the complete pipeline for creating a 3D virtual digital human—covering material shading, UDIM baking, PBR texture setup, facial and body rigging with Faceit and Auto‑Rig Pro, and animation using Mixamo, Atorcore and NVIDIA Audio2Face.
This comprehensive guide walks beginners through Blender's basic settings, interface layout, modeling workflow, and rendering options, offering practical tips, shortcut keys, and visual examples to help new users quickly master the software.
This article provides a comprehensive overview of UAV‑based oblique photogrammetry for real‑world 3D modeling, detailing background, step‑by‑step field capture, control‑point handling, aerial triangulation, model reconstruction, internal processing, and emerging trends in smart‑city applications.
This guide walks you through using Marvelous Designer to create detailed garment patterns, simulate cloth behavior, and seamlessly export OBJ files for integration with Cinema 4D, covering interface basics, pattern editing, sewing, motion testing, and final rendering to help beginners master 3D clothing workflows.
In a live broadcast on September 15 from 19:00 to 20:00, Taobao Technology and DataFun will feature architect Hu Xiaohang (Song Wu) discussing Taobao’s virtual e‑commerce innovations, including 3D/XR technology, e‑commerce‑driven technical entry points, digital home‑furnishing scene digitization, intelligent design tools, and methods to cut 3D modeling costs.
This article introduces Bilibili’s self‑developed BVA avatar file format, compares it with VRM, details its features such as unified model specifications, advanced material support, dynamic bone physics, and provides step‑by‑step Unity integration, export procedures for avatars, scenes, and runtime loading, along with sample code and resources.
This paper proposes a pix2pix‑based method to automatically generate green areas for large‑scale outdoor 3D scene modeling, detailing dataset creation via OpenCV segmentation, model training, region partitioning, and experimental results showing a 93.8% acceptance rate, significantly improving efficiency over manual drawing.
This case study explains how a UE4‑based visualization tool models building geometry, solar angles, and seasonal lighting to let users remotely assess residential daylight quality, improving decision‑making for families while optimizing performance through asset reduction and Git‑based workflow integration.
This article explains how an electronic sand table built with UE4 overcomes the limitations of physical models by offering realistic, data‑driven 3D visualizations of residential projects, detailing its modular resource library, intelligent generation rules, and the practical lessons learned during development.
This tutorial walks you through the complete workflow of preparing, optimizing, sculpting, organizing, and rigging a 3D donkey character in Cinema 4D, covering topology tools, sculpt mode, skeleton creation, controller adjustment, skin binding, and final animation tips.
This guide walks you through preparing an iPad with Apple Pencil, creating or importing a 3D model, coloring it in Procreate, exporting to USDZ, and using Reality Composer to add anchors, behaviors, and preview the AR experience directly on iOS devices.
BMW has launched a fully functional digital twin of its German factory in the metaverse, complete with 120 virtual employees, demonstrating how high‑fidelity simulations using tools like Omniverse, Character Creator, Actorcore, and mobile scanning apps enable risk‑free testing, rapid iteration, and new workflows across industries.
This article walks through the complete workflow of designing the Tiger Jiji IP, covering concept research, 3D nude modeling, high‑precision sculpting, UV unwrapping with RizomUV, material creation, lighting and rendering using OC, and final animation implementation with Lottie.
Recruit Cat, a B‑side recruitment app, leverages a Chinese‑style IP and blind‑box concept to convey positive energy, warmth, and fun, turning the brand into an emotional carrier that resonates with CEOs, managers, and HR, ultimately boosting user affinity and product reputation.
This guide walks you through creating a VR promotional video with C4D and Octane, covering project background, pre‑production planning, storyboard creation, 3D modeling, texturing, rigging, animation, lighting, rendering, and post‑production steps such as editing, color grading, audio, and voice‑over.
This guide walks you through using the lightweight Nomad digital sculpting app to create, refine, texture, and export 3D models—covering basic shape construction, detailed sculpting tools, Boolean operations, mesh smoothing, coloring, lighting, and final export for 3D printing.
This tutorial explains how to recreate Meta’s animated 3D logo by combining Three.js geometry, Blender modeling, FBX loading, custom materials, animation mixers, raycasting for interaction, and progress tracking, providing a complete step‑by‑step guide for web‑based 3D development.
From concept to 3D model, this article details how 58 Home’s new mascot ‘Dun Dun’ was conceived, designed, and animated—covering brand‑value integration, color strategy, brainstorming categories, sketch selection, 3D rendering, scene creation, and interactive animations that bring the character to life within the app.
This article explains why mesh regression is needed for 3D cloud design tools, defines mesh, outlines its application scenarios such as BIM plumbing, custom door windows, and hard‑floor tiles, and details a step‑by‑step design, implementation, bug detection methods, performance improvements, and future plans.
This article walks through BinaryVR’s art director Yoon’s end‑to‑end process for creating the real‑time 3D character Merry—from concept design and high‑poly sculpting to low‑poly retopology, UV mapping, texture painting, facial blendshape animation, Unity integration, and HyprFace SDK testing—showcasing techniques for AR/VR character pipelines.
This article walks through the complete production pipeline for the 2024 Spring Festival ‘Cow’ mascot, covering concept research, original illustration, low‑poly modeling, high‑detail sculpting, UV layout with RizomUV, material setup, lighting and rendering in C4D, and final Lottie‑based animation, offering practical tips and lessons learned.
This article introduces veteran 3D physical‑effects artist Zhu Dewei, explains the workflow of 3D printing, scanning, modeling and post‑processing for film props, and shares his insights on the challenges, skills and future of Chinese movie‑making through a detailed interview.
This tutorial walks you through creating a refined hollow dodecahedron ball ornament by generating a parametric topology, scaling for nested layers, editing polygons to bridge layers, and applying subdivision to achieve a smooth, interlocking structure, illustrating how complex forms follow predictable rules.
This roundup covers recent tech headlines—from Alibaba’s NeurIPS‑featured 3D AI model that turns 2D images into searchable 3D objects, to WeBank’s interest‑free rent‑loan extension, Honor’s staff integration plan, a critical iPhone remote‑control flaw, and links to deep‑dive articles on Linux kernel memory handling, command‑line productivity tools, and database cache consistency.
The presentation explains AR fundamentals, distinguishes it from AI and VR, and details a shoe‑try‑on system that captures 30 fps video, uses AI key‑point detection and pose estimation to overlay 3D shoe models—created via manual, scanning, or photogrammetry methods—rendered with GPU pipelines and PBR, enhanced by green‑screen occlusion and shadow techniques, earning positive audience feedback.
This article explores Blender’s open‑source origins, key advantages like cross‑platform support and comprehensive toolsets, guides beginners through installation and interface basics, showcases its capabilities from modeling to VFX, and offers practical tips for maximizing productivity in 3D projects.
This article outlines the full workflow of a game art team, covering its organizational structure, each phase of game development from project initiation to post‑launch, and the detailed art production steps—including style definition, 2D and 3D creation, UI animation, special effects, asset integration, testing, and launch.
This article walks through the concept sketching, abstract design, low‑poly 3D modeling, rigging with Mixamo, Octane rendering setup, lighting techniques, hair cloth simulation, and post‑processing steps used to create a promotional video for the youth‑focused FoxFriend social app.
The article presents a detailed technical interpretation of JD’s Design Help Open Platform, describing how it aggregates designers, leverages 3D modeling, VR, and fast rendering to solve the pain points of home‑decoration users, improve designer efficiency, and create a closed‑loop shopping experience.
This article introduces Cinema 4D, explains why beginners should choose it, outlines the main interface panels, suggests suitable tutorials, and offers a step‑by‑step learning method to help newcomers quickly become proficient in 3D modeling and animation.
Youku’s new video face‑swapping service lets users replace a celebrity’s face with a single uploaded photo by employing a 3D generative model, deep‑learning segmentation, multi‑scale super‑resolution, and trajectory smoothing to achieve fast, near‑photorealistic results across varied angles, expressions, and lighting, though it still lacks personalized models and struggles with extreme side views or heavy occlusions.
This article describes how Lianjia's Ke Holdings launched VR house viewing technology, detailing the 3D scanning process, machine‑learning‑assisted modeling, immersive interactive features, development challenges, and cross‑team collaboration that brought immersive VR tours to over a million property listings.
