• Corpus ID: 220381395

Wasserstein Distances for Stereo Disparity Estimation

  title={Wasserstein Distances for Stereo Disparity Estimation},
  author={Divyansh Garg and Yan Wang and Bharath Hariharan and Mark E. Campbell and Kilian Q. Weinberger and Wei-Lun Chao},
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values… 

Figures and Tables from this paper

PLUMENet: Efficient 3D Object Detection from Stereo Images
This paper directly construct a pseudo LiDAR feature volume in 3D space, which is then used to solve both depth estimation and object detection tasks and achieves state-of-the-art performance with much faster inference times when compared to existing methods on the challenging KITTI benchmark.
SMD-Nets: Stereo Mixture Density Networks
This paper proposes Stereo Mixture Density Networks (SMD-Nets), a simple yet effective learning framework compatible with a wide class of 2D and 3D architectures which ameliorates both issues of stereo matching accuracy and depth accuracy.
Parallel Dense Binary Stereo Matching Using CUDA
This paper addresses the problem of dense stereo matching from two rectified images without prior information about the structure of the scene by porting the whole pipeline to the GPU and utilizing an outstanding aggregation technique that is followed by a hybrid matching metric which is proved to enhance the matching accuracy.
Towards Continual, Online, Unsupervised Depth
Regularization and replay-based methods without task boundaries are proposed to avoid catastrophic forgetting while adapting to online data and results of forgetting as well as adaptation are provided, which are superior to recent methods.
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector
This work proposes LIGA-Stereo (LiDAR Geometry Aware Stereo Detector) to learn stereo-based 3D detectors under the guidance of high-level geometry-aware representations of LiDAR-based detection models, and finds existing voxel-based stereo detectors failed to learn semantic features effectively from indirect 3D supervisions.
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
Without bells and whistles, extensive experiments in various modality setups on the popular KITTI benchmark show that the stereo modeling approach, DSGN++, consistently outperforms other camera-based 3D detectors for all categories.
3D Object Detection from Images for Autonomous Driving: A Survey
This paper provides the first comprehensive survey of this novel and continuously growing research field, summarizing the most commonly used pipelines for image-based 3D detection and deeply analyzing each of their components and proposing two new taxonomies to organize the state-of-the-art methods into different categories.
3D Object Detection for Autonomous Driving: A Review and New Outlooks
Autonomous driving, in recent years, has been receiving increasing attention for its potential to relieve drivers’ burdens and improve the safety of driving. In modern autonomous driving pipelines,
Stereo Neural Vernier Caliper
A new object-centric framework for learning- based stereo 3D object detection that achieves state-of-the-art performance on the KITTI benchmark is proposed.
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
A simple pixel-wise contrastive learning across the viewpoints for generalization of stereo matching performance to unseen domains is proposed, which achieves superior performance over several state-of-the-art networks.


Anytime Stereo Image Depth Estimation on Mobile Devices
This work proposes a novel approach for disparity prediction in the anytime setting that can trade off computation and accuracy at inference time, and can process $1242 \times 375$ resolution images within a range of 10-35 FPS on an NVIDIA Jetson TX2 module with only marginal increases in error.
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
This paper proposes to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities and achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks.
SegStereo: Exploiting Semantic Information for Disparity Estimation
This paper suggests that appropriate incorporation of semantic cues can greatly rectify prediction in commonly-used disparity estimation frameworks and proposes a unified model SegStereo, which employs semantic features from segmentation and introduces semantic softmax loss, which helps improve the prediction accuracy of disparity maps.
Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
This paper proposes to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal, and achieves impressive improvements over the existing state-of-the-art in image- based performance.
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
  • Jiaming Sun, Linghao Chen, H. Bao
  • Computer Science, Environmental Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
It is proposed to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes the Disp R-CNN system more widely applicable.
Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation
A new optimization algorithm is proposed for the authors' SLIC-like objective which preserves connecteness of image segments and exploits shape regularization in the form of boundary length and can be achieved an order of magnitude faster than competing approaches.
Object-Centric Stereo Matching for 3D Object Detection
This work proposes a novel 2D box association and object-centric stereo matching method that only estimates the disparities of the objects of interest to address disparity and achieves state-of-the-art results on the KITTI 3D and BEV benchmarks.
DSGN: Deep Stereo Geometry Network for 3D Object Detection
The Deep Stereo Geometry Network (DSGN), for the first time, provides a simple and effective one-stage stereo-based 3D detection pipeline that jointly estimates the depth and detects 3D objects in an end-to-end learning manner.
High-accuracy stereo depth maps using structured light
  • Daniel Scharstein, R. Szeliski
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
A method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light that does not require the calibration of the light sources and yields registered disparity maps between all pairs of cameras and illumination projectors.
Realtime 3D Object Detection for Automated Driving Using Stereo Vision and Semantic Information
This work proposes a 3D object detection and pose estimation method for automated driving using stereo images that focuses not only on cars, but on all types of road users and can ensure real-time capability through GPU implementation of the entire processing chain.