Type a name, or just describe what you need. Results blend keyword and meaning-based search. 34 matches, each with an EU availability status.
Model
Feed-forward system that turns an RGB image or video into editable, textured per-object 3D meshes in under a minute.
Research
Post-training method that refines feed-forward 3D reconstruction models (Pi3, DA3, VGGT) on unlabeled video.
3D reconstruction model that recovers geometry and camera poses from photos or video using a loop transformer.
Research · Preferred Networks
Generative method from Preferred Networks that reconstructs high-resolution 3D scene meshes from posed multi-view images.
Research framework that turns posed images with instance masks and 3D boxes into per-object meshes for cluttered scenes.
Research method that reconstructs complete 4D (3D plus time) scenes from a single monocular video using Gaussian Splatting.
Agentic framework that reconstructs sim-ready 3D scenes with rigid, articulated and deformable objects from multi-view RGB.
Model · Meta
Meta research framework that aligns a frozen SAM 3D model to input images or video at inference time for 3D reconstruction.
Research method that reconstructs PBR-ready indoor 3D scene meshes from multi-view images using a Trellis.2 generative prior.
Research framework for globally consistent 3D reconstruction from long RGB videos using chunked priors and test-time adaptation.
Model · Nvidia
Feed-forward model that repairs lifted 2D tracks and depth into accurate dense 3D trajectories from monocular video.
Feed-forward 3D Gaussian Splatting model that reconstructs scenes from arbitrary input views, with or without camera poses.
Feed-forward 3D scene reconstruction model that outputs triangle primitives directly usable as meshes for simulation.
Training-free research system that reconstructs simulation-ready 4D mesh scenes from a single monocular video.
Research method that reconstructs a 4D Gaussian Splatting human from a single casual monocular video.
Model · NVIDIA
NVIDIA's 117M-parameter looped transformer for multi-view 3D reconstruction of camera poses and dense geometry.
Research method that rigs animatable Gaussian characters with an inner kinematic skeleton and outer free-form bones.
Multi-view video diffusion model that turns monocular or sparse videos of dynamic humans into dense multi-view videos for 4D Gaussian splats.
Research · ByteDance
ByteDance research pipeline that turns indoor captures into editable, simulation-ready 3D scenes of separate object meshes.
Research method that reconstructs 3D surfaces from a variable number of unposed images using flow matching.
Research method that builds controllable, articulated 3D object models from keypoints, point clouds or depth video.
Video-diffusion LoRA that repairs artifacts in 3DGS, NeRF, mesh and point-cloud renders while keeping the camera path.
Research · Google
Research method for free-view rendering and relighting of full-body dynamic humans from four sparse RGB views.
Research method that recovers 6-DoF object and camera pose from monocular video via proxy-video translation and PnP.
