Tagged articles

image-to-3D

3 articles · Page 1 of 1

Sep 28, 2026 · Artificial Intelligence

SceneMosaic: Fast, Diverse 3D Scene Generation from a Single Image

SceneMosaic generates diverse, physically valid 3D room layouts from a single image by combining image priors for speed, agent-based layout evolution for accuracy, and local patch decomposition for combinatorial diversity, achieving 24x speedup over baselines with zero collision rate.

3D scene generationSceneMosaicagent-based

0 likes · 12 min read

SceneMosaic: Fast, Diverse 3D Scene Generation from a Single Image

AI Open-Source Efficiency Guide

Jul 21, 2026 · Artificial Intelligence

img2threejs: Turn One Image into Animated Three.js Code with 8-Pass AI Pipeline

img2threejs is an open-source AI Agent skill that reconstructs a single reference image into an editable, animation-ready Three.js procedural model through an 8-pass sculpting pipeline with AI visual self-correction, outputting TypeScript code instead of binary meshes.

AI agentPythonQuality Gates

0 likes · 16 min read

img2threejs: Turn One Image into Animated Three.js Code with 8-Pass AI Pipeline

Design Hub

Dec 18, 2025 · Artificial Intelligence

From Images to 3D and Flat to Layered: Two AI Technologies Set to Reshape Design Workflows

The article examines Microsoft’s open‑source T‑RELLIS .2 model that turns 2D sketches into high‑fidelity 3D assets in seconds and Qwen‑Image‑Layered, a diffusion‑based system that decomposes images into editable RGBA layers, highlighting their architectures, performance benchmarks, and implications for designers.

AIQwen-Image-LayeredT-RELLIS

0 likes · 8 min read

From Images to 3D and Flat to Layered: Two AI Technologies Set to Reshape Design Workflows