skip to main content

This content will become publicly available on December 1, 2022

Title: 3DVNet: Multi-View Depth Prediction and Volumetric Refinement
We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.
; ; ;
Award ID(s):
Publication Date:
Journal Name:
2021 International Conference on 3D Vision (3DV)
Page Range or eLocation-ID:
700 to 709
Sponsoring Org:
National Science Foundation
More Like this
  1. Synthetic data is highly useful for training machine learning systems performing image-based 3D reconstruction, as synthetic data has applications in both extending existing generalizable datasets and being tailored to train neural networks for specific learning tasks of interest. In this paper, we introduce and utilize a synthetic data generation suite capable of generating data given existing 3D scene models as input. Specifically, we use our tool to generate image sequences for use with Multi-View Stereo (MVS), moving a camera through the virtual space according to user-chosen camera parameters. We evaluate how the given camera parameters and type of 3D environmentmore »affect how applicable the generated image sequences are to the MVS task using five pre-trained neural networks on image sequences generated from three different 3D scene datasets. We obtain generated predictions for each combination of parameter value and input image sequence, using standard error metrics to analyze the differences in depth predictions on image sequences across 3D datasets, parameters, and networks. Among other results, we find that camera height and vertical camera viewing angle are the parameters that cause the most variation in depth prediction errors on these image sequences.« less
  2. We propose a system that uses a convolution neural network (CNN) to estimate depth from a stereo pair followed by volumetric fusion of the predicted depth maps to produce a 3D reconstruction of a scene. Our proposed depth refinement architecture, predicts view-consistent disparity and occlusion maps that helps the fusion system to produce geometrically consistent reconstructions. We utilize 3D dilated convolutions in our proposed cost filtering network that yields better filtering while almost halving the computational cost in comparison to state of the art cost filtering architectures. For feature extraction we use the Vortex Pooling architecture [24]. The proposed methodmore »achieves state of the art results in KITTI 2012, KITTI 2015 and ETH 3D stereo benchmarks. Finally, we demonstrate that our system is able to produce high fidelity 3D scene reconstructions that outperforms the state of the art stereo system.« less
  3. We propose a boundary-aware multi-task deep-learning- based framework for fast 3D building modeling from a sin- gle overhead image. Unlike most existing techniques which rely on multiple images for 3D scene modeling, we seek to model the buildings in the scene from a single overhead im- age by jointly learning a modified signed distance function (SDF) from the building boundaries, a dense heightmap of the scene, and scene semantics. To jointly train for these tasks, we leverage pixel-wise semantic segmentation and normalized digital surface maps (nDSM) as supervision, in addition to labeled building outlines. At test time, buildings in themore »scene are automatically modeled in 3D using only an input overhead image. We demonstrate an increase in building modeling performance using a multi-feature net- work architecture that improves building outline detection by considering network features learned for the other jointly learned tasks. We also introduce a novel mechanism for ro- bustly refining instance-specific building outlines using the learned modified SDF. We verify the effectiveness of our method on multiple large-scale satellite and aerial imagery datasets, where we obtain state-of-the-art performance in the 3D building reconstruction task.« less
  4. This work provides an architecture that incorporates depth and tactile information to create rich and accurate 3D models useful for robotic manipulation tasks. This is accomplished through the use of a 3D convolutional neural network (CNN). Offline, the network is provided with both depth and tactile information and trained to predict the object’s geometry, thus filling in regions of occlusion. At runtime, the network is provided a partial view of an object. Tactile information is acquired to augment the captured depth information. The network can then reason about the object’s geometry by utilizing both the collected tactile and depth information.more »We demonstrate that even small amounts of additional tactile information can be incredibly helpful in reasoning about object geometry. This is particularly true when information from depth alone fails to produce an accurate geometric prediction. Our method is benchmarked against and outperforms other visual-tactile approaches to general geometric reasoning. We also provide experimental results comparing grasping success with our method.« less
  5. The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2Dmore »convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks including multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method.« less