Recovering Detail in 3D Shapes Using Disparity Maps
Not on the map. Why?
Abstract (arXiv)
We present a fine-tuning method to improve the appearance of 3D geometries reconstructed from single images. We leverage advances in monocular depth estimation to obtain disparity maps and present a novel approach to transforming 2D normalized disparity maps into 3D point clouds by using shape priors to solve an optimization on the relevant camera parameters. After creating a 3D point cloud from disparity, we introduce a method to combine the new point cloud with existing information to form a more faithful and detailed final geometry. We demonstrate the efficacy of our approach with multiple experiments on both synthetic and real images.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 64 references that are in the map. First posted on arXiv 1 Jul 2022.
Builds on
44 of 64 references.
References · 44
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
- 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
32 more
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
- 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
- 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
- 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
- 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
- 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
- 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
- 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
- 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
- 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
- 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
- 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
- 2016Single-Image Depth Perception in the Wildcited by 179
- 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 146
- 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
- 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
- 2014Deep Convolutional Neural Fields for Depth Estimation from a Single Imagecited by 106
- 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
- 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
- 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
- 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
- 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
- 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
- 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
- 2020Implicit Mesh Reconstruction from Unannotated Image Collectionscited by 49
- 2017OctNetFusion: Learning Depth Fusion from Datacited by 45
- 2018Single View Stereo Matchingcited by 39
- 2018Deep attention-based classification network for robust depth predictioncited by 36
- 2018Pixels, voxels, and views: A study of shape representations for single view 3D object shape predictioncited by 27
- 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26
- 20203D Reconstruction of Novel Object Shapes from Single Imagescited by 21
Built on by
Not cited yet.