Dieses Projekt ist ein RGB-D-Image-Inpainting-Tool und Framework für die 3D-Fotorekonstruktion. Es transformiert einzelne 2D-Bilder in 3D-Inhalte, indem es monokulare Tiefe schätzt und fehlende Farb- und Tiefendaten synthetisiert, um verdeckte Bereiche aufzufüllen.
Die Hauptfunktionen von vt-vl-lab/3d-photo-inpainting sind: Inpainting Tools, Single-Image 3D Reconstructions, Monocular Depth Estimators, Depth Estimation, Image Inpainting, Novel View Synthesis Engines, Multi-View Video Synthesis, Novel View Synthesizers.
Open-Source-Alternativen zu vt-vl-lab/3d-photo-inpainting sind unter anderem: bytedance-seed/depth-anything-3 — Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation,… apple/ml-sharp — ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to… isl-org/midas — MiDaS is a PyTorch computer vision library and monocular depth estimation model designed to predict scene depth from… depthanything/depth-anything-v2 — Depth-Anything-V2 is a computer vision foundation model designed for general-purpose spatial understanding and depth… aaronjackson/vrn — vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from… nv-tlabs/get3d — GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and…
Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve
ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to predict 3D geometry and appearance from a single photograph in a single feedforward pass. The system generates metric 3D scene representations and includes a real-time view synthesizer for producing high-resolution images of new viewpoints. It also features a camera trajectory renderer that creates video sequences by moving a virtual camera through the predicted 3D space. The project covers coordinate-based neural rendering, 3D Gaussian representation regression, and real-ti
Depth-Anything-V2 is a computer vision foundation model designed for general-purpose spatial understanding and depth perception. It functions as a monocular depth estimation model that predicts relative and absolute depth maps from single images or video sequences. The project provides specialized tools for both relative depth estimation and metric depth calculation, allowing for the determination of absolute physical distances in indoor and outdoor environments. It includes a video depth estimation framework that ensures temporal consistency across sequential frames to maintain stable depth
MiDaS is a PyTorch computer vision library and monocular depth estimation model designed to predict scene depth from single images. It functions as a scene depth predictor that computes distance maps to determine object proximity to the camera. The project enables zero-shot depth transfer, allowing the model to be applied to new datasets or environments without additional training data. It focuses on relative depth regression to predict scale-invariant depth maps. The library includes a real-time depth visualizer for capturing live camera feeds and displaying corresponding depth maps. It als