GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion

• URL: http://arxiv.org/abs/2412.06080v1
• Date: Sun, 08 Dec 2024 22:04:34 GMT
• Title: GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion
• Authors: Karlo Koledic, Luka Petrovic, Ivan Markovic, Ivan Petrovic,
• Abstract summary: Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature. We propose a novel canonical representation that maintains consistency across varied camera setups. We also propose a novel architecture that adaptively and probabilistically fuses depths estimated via object size and vertical image position cues.
• Score: 7.588468985212172
• License:
• Abstract: Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot accuracy. This challenge is particularly evident in autonomous vehicles and mobile robotics, where data is collected with fixed camera setups, limiting the geometric diversity. Yet, this context also presents an opportunity: the fixed relationship between the camera and the ground plane imposes additional perspective geometry constraints, enabling depth regression via vertical image positions of objects. However, this cue is highly susceptible to overfitting, thus we propose a novel canonical representation that maintains consistency across varied camera setups, effectively disentangling depth from specific parameters and enhancing generalization across datasets. We also propose a novel architecture that adaptively and probabilistically fuses depths estimated via object size and vertical image position cues. A comprehensive evaluation demonstrates the effectiveness of the proposed approach on five autonomous driving datasets, achieving accurate metric depth estimation for varying resolutions, aspect ratios and camera setups. Notably, we achieve comparable accuracy to existing zero-shot methods, despite training on a single dataset with a single-camera setup.

Related papers

• Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers [39.14931758754381]
  We introduce a novel fusion method that bypasses monocular depth estimation altogether. We show that our model can modulate its use of camera features based on the availability of lidar features.
  arXiv  Detail & Related papers  (2023-12-22T18:51:50Z)
• GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding [8.289857214449372]
  GenDepth is a novel model capable of performing metric depth estimation for arbitrary vehicle-camera setups. We propose a novel embedding of camera parameters as the ground plane depth and present a novel architecture that integrates these embeddings with adversarial domain alignment. We validate GenDepth on several autonomous driving datasets, demonstrating its state-of-the-art generalization capability for different vehicle-camera systems.
  arXiv  Detail & Related papers  (2023-12-10T22:28:34Z)
• GEDepth: Ground Embedding for Monocular Depth Estimation [4.95394574147086]
  This paper proposes a novel ground embedding module to decouple camera parameters from pictorial cues. A ground attention is designed in the module to optimally combine ground depth with residual depth. Experiments reveal that our approach achieves the state-of-the-art results on popular benchmarks.
  arXiv  Detail & Related papers  (2023-09-18T17:56:06Z)
• Multi-Modal Dataset Acquisition for Photometrically Challenging Object [56.30027922063559]
  This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition pipeline that enhances existing 3D perception and 6D object pose datasets.
  arXiv  Detail & Related papers  (2023-08-21T10:38:32Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• Robust Self-Supervised Extrinsic Self-Calibration [25.727912226753247]
  Multi-camera self-supervised monocular depth estimation from videos is a promising way to reason about the environment. We introduce a novel method for extrinsic calibration that builds upon the principles of self-supervised monocular depth and ego-motion learning.
  arXiv  Detail & Related papers  (2023-08-04T06:20:20Z)
• FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scene [57.26600120397529]
  It has long been an ill-posed problem to predict absolute depth maps from single images in real (unseen) indoor scenes. We develop a focal-and-scale depth estimation model to well learn absolute depth maps from single images in unseen indoor scenes.
  arXiv  Detail & Related papers  (2023-07-27T04:49:36Z)
• Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation [75.99435808648784]
  We propose a novel multi-camera collaborative depth prediction method. It does not require large overlapping areas while maintaining structure consistency between cameras. Experimental results on DDAD and NuScenes datasets demonstrate the superior performance of our method.
  arXiv  Detail & Related papers  (2022-10-05T03:44:34Z)
• SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation [101.55622133406446]
  We propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets.
  arXiv  Detail & Related papers  (2022-04-07T17:58:47Z)
• Robust Consistent Video Depth Estimation [65.53308117778361]
  We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. Our algorithm combines two complementary techniques: (1) flexible deformation-splines for low-frequency large-scale alignment and (2) geometry-aware depth filtering for high-frequency alignment of fine depth details. In contrast to prior approaches, our method does not require camera poses as input and achieves robust reconstruction for challenging hand-held cell phone captures containing a significant amount of noise, shake, motion blur, and rolling shutter deformations.
  arXiv  Detail & Related papers  (2020-12-10T18:59:48Z)

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.