Generative method from Preferred Networks that reconstructs high-resolution 3D scene meshes from posed multi-view images.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
T3lescope is a research method from Preferred Networks for reconstructing 3D scene meshes from posed multi-view images without per-scene optimization. It uses mesh flow models to output a high-resolution mesh directly, and works across scales from single objects to large outdoor and city-scale scenes.
A single fixed-resolution generator is applied in an inference-time coarse-to-fine cascade. A coarse level establishes the scene layout, and finer levels perturb and denoise inherited geometry within progressively smaller spatial cells to recover surface detail. The model is trained on individual cells at multiple scales with shared weights, so the number of levels, cell scales and cell locations are chosen at inference time.
According to the authors, it outperforms feed-forward and generative baselines on indoor, outdoor and city-scale scenes, matches or surpasses per-scene optimization, and recovers glossy and transparent surfaces. Comparisons are shown against GaussianWrapping, GenRecon and CityGaussianV2. The demos use roughly 56 to 256 input views. The project is a research release with a project page and an arXiv paper; the provided material does not show released code or weights (a creator review mentioned code is coming soon).
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Generative model that turns photos of a scene into a detailed 3D mesh using a coarse-to-fine approach, handling shiny and glass surfaces. It shows much more detail than Gaussian wrapping but needs many photos; code is coming soon.
Closest neighbours by meaning, not just by category.
Model
Feed-forward 3D scene reconstruction model that outputs triangle primitives directly usable as meshes for simulation.
Research
Research method that reconstructs PBR-ready indoor 3D scene meshes from multi-view images using a Trellis.2 generative prior.
Research
Post-training method that refines feed-forward 3D reconstruction models (Pi3, DA3, VGGT) on unlabeled video.
Model · Meta
Meta research framework that aligns a frozen SAM 3D model to input images or video at inference time for 3D reconstruction.
Model
Feed-forward 3D Gaussian Splatting model that reconstructs scenes from arbitrary input views, with or without camera poses.
Model · World Labs
World Labs' world model that generates and reconstructs explorable 3D worlds from images, text, video or 3D input.
