Roboflow

3D Reconstruction Models

The one 3D reconstruction model in our catalog.

1 model · 1 open-weight · prices synced Oct 26, 2026

Open-Source 3D Reconstruction Models

1 model with downloadable weights you can self-host under their licenses (Custom).

Meta
SAM 3D Objects
SAM 3D Objects is a 3D reconstruction model released on November 19, 2025 by Meta AI as part of the broader SAM 3 release. It extends the Segment Anything Model family from 2D segmentation into 3D object reconstruction, predicting geometry, texture, and spatial layout for individual objects from a single RGB image. Given an image together with a prompt identifying the object (a segmentation mask, point, or bounding box), the model outputs a full textured 3D mesh, without requiring multi-view captures, depth sensors, or known camera parameters.SAM 3D Objects uses a two-stage transformer architecture: a coarse stage that predicts 3D shape and object pose, followed by a refinement stage that adds texture and surface detail, with DINOv2 used to encode the input image. The model is trained via a human-and-model-in-the-loop data engine that combines synthetic 3D assets with real-image annotations, producing approximately 3.14 million mesh annotations across nearly 1 million images. Meta released SAM 3D Objects alongside SAM 3D Body, a companion model for single-image human mesh recovery, and SAM 3D Artist Objects (SA-3DAO), a new evaluation benchmark assembled with artist-created 3D ground truth. The model is designed as a companion to SAM 3 for downstream applications including augmented reality, robotics, content creation, and visual effects; it already powers the View in Room feature on Facebook Marketplace. SAM 3D Objects is released under the SAM 3 license; users should review the license terms prior to commercial use.

How to Choose a 3D Reconstruction Model

Reconstruction methods differ in what they need as input and what they produce: measurable geometry, renderable scenes, or a plausible shape from one photo. Start from the output you actually need.

Structure-from-motion plus multi-view stereo triangulates real geometry from many overlapping photos, producing point clouds and meshes with real-world scale (given a reference). It remains the standard for scanning, surveying, and any application where dimensions must be trusted.

NeRFs and 3D Gaussian splatting fit a scene representation that renders photoreal novel views from ordinary photo or video capture, with splatting fast enough for interactive use. They excel at walkthroughs, AR content, and digital twins for viewing; extracting clean, measurable meshes from them is still the weaker path.

Monocular depth and single-image reconstruction predict plausible geometry from one photo using learned priors. The result is a good relative structure for effects, editing, and robotics heuristics, but it is an estimate: when accuracy matters and you can capture more views, do.

The bottom line: Measurements need photogrammetry, immersive viewing favors neural rendering, and single-image methods trade accuracy for convenience when one photo is all you have.

This page lists the one 3D reconstruction models in the Roboflow Playground catalog, all of them open-weight and free to self-host. Compare licenses, parameters, and release dates side by side, or open any model page for full details.