Deep Planar Parallax for Monocular Depth Estimation

• URL: http://arxiv.org/abs/2301.03178v2
• Date: Tue, 28 Nov 2023 09:07:46 GMT
• Title: Deep Planar Parallax for Monocular Depth Estimation
• Authors: Haoqian Liang, Zhichao Li, Ya Yang, Naiyan Wang
• Abstract summary: In-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling. We also propose Planar Position Embedding to handle dynamic objects that defy static scene assumptions.
• Score: 24.801102342402828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling, leading to substantial performance enhancement. Additionally, we propose Planar Position Embedding (PPE) to handle dynamic objects that defy static scene assumptions and to tackle slope variations that are challenging to differentiate. Comprehensive experiments on autonomous driving datasets, namely KITTI and the Waymo Open Dataset (WOD), prove that our Planar Parallax Network (PPNet) significantly surpasses existing learning-based methods in performance.

Related papers

• Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation [38.81275292687583]
  We propose Plane2Depth, which adaptively utilizes plane information to improve depth prediction within a hierarchical framework. In the proposed plane guided depth generator (PGDG), we design a set of plane queries as prototypes to softly model planes in the scene and predict per-pixel plane coefficients. In the proposed adaptive plane query aggregation (APGA) module, we introduce a novel feature interaction approach to improve the aggregation of multi-scale plane features.
  arXiv  Detail & Related papers  (2024-09-04T07:45:06Z)
• OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments [77.0399450848749]
  We propose an OccNeRF method for training occupancy networks without 3D supervision. We parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range. For semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model.
  arXiv  Detail & Related papers  (2023-12-14T18:58:52Z)
• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [64.04617968947697]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• Self-Supervised Learning based Depth Estimation from Monocular Images [0.0]
  The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB image as input. We plan to do intrinsic camera parameters during training and apply weather augmentations to further generalize our model.
  arXiv  Detail & Related papers  (2023-04-14T07:14:08Z)
• SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes [58.89295356901823]
  Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions. We introduce an external pretrained monocular depth estimation model for generating single-image depth prior. Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
  arXiv  Detail & Related papers  (2022-11-07T16:17:47Z)
• Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry [4.620624344434533]
  Supervised learning depth estimation methods can achieve good performance when trained on high-quality ground-truth, like LiDAR data. We propose a novel approach combining structure information from a promising Plane and Parallax geometry pipeline with depth information into a U-Net supervised learning network. Our model has impressive performance on depth prediction of thin objects and edges, and compared to structure prediction baseline, our model performs more robustly.
  arXiv  Detail & Related papers  (2022-07-13T17:04:05Z)
• TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo [55.30992853477754]
  We present TANDEM, a real-time monocular tracking and dense framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of alignments. TANDEM shows state-of-the-art real-time 3D reconstruction performance.
  arXiv  Detail & Related papers  (2021-11-14T19:01:02Z)
• Self-Supervised Monocular Depth Estimation with Internal Feature Fusion [12.874712571149725]
  Self-supervised learning for depth estimation uses geometry in image sequences for supervision. We propose a novel depth estimation networkDIFFNet, which can make use of semantic information in down and upsampling procedures.
  arXiv  Detail & Related papers  (2021-10-18T17:31:11Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)
• SLPC: a VRNN-based approach for stochastic lidar prediction and completion in autonomous driving [63.87272273293804]
  We propose a new LiDAR prediction framework that is based on generative models namely Variational Recurrent Neural Networks (VRNNs) Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames. We present a sparse version of VRNNs and an effective self-supervised training method that does not require any labels.
  arXiv  Detail & Related papers  (2021-02-19T11:56:44Z)
• Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues [24.743099160992937]
  We propose a novel self-supervised joint learning framework for depth estimation. The proposed framework outperforms the state-of-the-art(SOTA) on KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2020-06-17T13:56:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.