Speridlabs (Alejandro Cañada, Chema Garabito) · Image-to-3D splats

Idol

Idol is a 0.66B-parameter model from Speridlabs that turns a single image (a photograph, a render or an Iris-3B generation) into a 3D object made of Gaussians, including sides the image did not show. Each object can be generated at several levels of detail, from 32,768 to 1,048,576 Gaussians, and the model runs in under 8 GB of GPU memory. On the authors' benchmark, one H100 per model, Idol scores 0.781 DINOv2 and 0.885 CLIP on new views, against 0.743 and 0.868 for TripoSplat, 0.754 and 0.868 for TRELLIS, and 0.575 and 0.784 for LGM. Request time is 6.8 s for Idol at 50 steps and 262,144 Gaussians, compared with 9.9 s for TripoSplat, 7.1 s for TRELLIS and 1.1 s for LGM. LGM has the highest input-view PSNR (12.46 against Idol's 12.25), which the authors attribute to PSNR averaging squared pixel error despite visibly blurry results. Median request time for 262,144 Gaussians ranges from 3.4 s on a B300 to 54.6 s on an L4. The page links a demo, code and weights, but does not state a licence or release version.

Open the source ↗

Similar 3D & Spatial releases

  • JST-2

    Viggle AI · World Model · Week 44, 2026

  • Viggle AI

    Viggle Inc. · 3D Generation · Week 20, 2026

  • Viggle PINOC

    Viggle AI · 3D Generation · Week 20, 2026

  • InfiniSplat v2

    Zhejiang University, Shenzhen University, Hello TransTech and Causa Robotics · Feed-Forward Gaussian Splatting · Week 43, 2026

  • UniForge3D

    Peking University, Math Magic and HKUST · Image-to-3D · Week 43, 2026

  • GaussiAnimate

    Westlake University, Nanjing University, HKU and MUST · 4D Rigging · Week 43, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.