---
title: "DUSt3R"
description: "NAVER Labs two-view pointmaps, no calibration. Runner verified on the bundled multi-view case. CC-BY-NC-SA-4.0. Writes dust3r_point_cloud.ply."
modelId: "dust3r"
pageSource: authored
---

DUSt3R made unconstrained two-view 3D easy: **two images**, no calibration, no poses — it regresses aligned **pointmaps**. WorldFoundry vendors it under `worldfoundry/base_models/three_dimensions/general_3d/dust3r` and exposes `DUSt3RPipeline` on the shared geometry-prior contract. Aliases `naver-dust3r` and `geometric-3d-vision-made-easy` resolve here.

<ModelPaperFigures modelId="dust3r" locale="en" />

Paper: [DUSt3R: Geometric 3D Vision Made Easy](https://arxiv.org/abs/2312.14132) (arXiv 2312.14132). Project: [dust3r.europe.naverlabs.com](https://dust3r.europe.naverlabs.com/). Publisher: NAVER Labs Europe. License: **CC-BY-NC-SA-4.0** (non-commercial downstream).

Runner is **verified**: checkpoint-backed Studio inference produced a finite point cloud from the bundled multi-view test case (`inference_evidence.yaml`).

<ModelCommandBuilder modelId="dust3r" locale="en" />

## What it is for

Launch `worldfoundry-eval run dust3r` with the feed-forward multi-view reconstruction profile. Required: `image`. Optional: `prompt`, `video`. `actions`: `multi_view_reconstruction`. Artifact: `dust3r_point_cloud.ply`. Large scenes still need global alignment, which gets expensive with many views. Streaming metric state is [CUT3R](/docs/guides/supported-models/cut3r), not this pairwise card.

## Runtime contract

`DUSt3RPipeline` on the shared geometry-prior contract (`dust3r-base-model`). Required: `image` (an uncalibrated pair or multi-view set). Optional catalog fields: `prompt`, `video`. `actions`: `multi_view_reconstruction`. Artifact: `dust3r_point_cloud.ply`.

| Knob | Recorded |
| --- | --- |
| Checkpoint | `naver/DUSt3R_ViTLarge_BaseDecoder_512_dpt` → `$WORLDFOUNDRY_CKPT_DIR/DUSt3R_ViTLarge_BaseDecoder_512_dpt.pth` |
| Encoder | ViT-Large + Base decoder, **512** DPT |
| Pair output | Per-pixel pointmaps in a shared frame (camera-1 coordinates) |
| Many views | Global alignment after pairwise inference |
| Runner | **verified** — finite point cloud from the bundled multi-view Studio case (`inference_evidence.yaml`) |

Environment: `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8). Catalog VRAM is unset. License: **CC-BY-NC-SA-4.0**.

## Running in WorldFoundry

Stage the NAVER `512_dpt` file first. Missing weights fail at load — the runtime does not download them. Respect NC-SA terms downstream.

<ModelRelatedRecipes modelId="dust3r" locale="en" />