3D Scene Reconstruction
37 papers with code • 0 benchmarks • 3 datasets
Creating 3D scene either using conventional SFM pipelines or latest deep learning approaches.
Benchmarks
These leaderboards are used to track progress in 3D Scene Reconstruction
Most implemented papers
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
We present a novel framework named NeuralRecon for real-time 3D scene reconstruction from a monocular video.
The Replica Dataset: A Digital Replica of Indoor Spaces
We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale.
CoReNet: Coherent 3D scene reconstruction from a single RGB image
Furthermore, we adapt our model to address the harder task of reconstructing multiple objects from a single image.
UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction
When compared to monocular pre-training methods on the nuScenes dataset, UniScene shows a significant improvement of about 2. 0% in mAP and 2. 0% in NDS for multi-camera 3D object detection, as well as a 3% increase in mIoU for surrounding semantic scene completion.
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
We present an automated and efficient approach for retrieving high-quality CAD models of objects and their poses in a scene captured by a moving RGB-D camera.
DeepV2D: Video to Depth with Differentiable Structure from Motion
We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video.
Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
Depth sensing is crucial for 3D reconstruction and scene understanding.
Atlas: End-to-End 3D Scene Reconstruction from Posed Images
Traditional approaches to 3D reconstruction rely on an intermediate representation of depth maps prior to estimating a full 3D model of a scene.
GRF: Learning a General Radiance Field for 3D Representation and Rendering
We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations.
Learning to Recover 3D Scene Shape from a Single Image
Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in mixed-data depth prediction training, and possible unknown camera focal length.