Dynamic Depth-Supervised NeRF for Multi-View RGB-D Operating Room Images

• URL: http://arxiv.org/abs/2211.12436v2
• Date: Wed, 30 Aug 2023 08:40:16 GMT
• Title: Dynamic Depth-Supervised NeRF for Multi-View RGB-D Operating Room Images
• Authors: Beerend G.A. Gerats, Jelmer M. Wolterink, Ivo A.M.J. Broeders
• Abstract summary: We show that NeRF can be used to render synthetic views from arbitrary camera positions in the operating room. We show that regularisation with depth supervision from RGB-D sensor data results in higher image quality. Our results show the potential of a dynamic NeRF for view synthesis in the OR and stress the relevance of depth supervision in a clinical setting.
• Score: 1.6451639748812472
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The operating room (OR) is an environment of interest for the development of sensing systems, enabling the detection of people, objects, and their semantic relations. Due to frequent occlusions in the OR, these systems often rely on input from multiple cameras. While increasing the number of cameras generally increases algorithm performance, there are hard limitations to the number and locations of cameras in the OR. Neural Radiance Fields (NeRF) can be used to render synthetic views from arbitrary camera positions, virtually enlarging the number of cameras in the dataset. In this work, we explore the use of NeRF for view synthesis of dynamic scenes in the OR, and we show that regularisation with depth supervision from RGB-D sensor data results in higher image quality. We optimise a dynamic depth-supervised NeRF with up to six synchronised cameras that capture the surgical field in five distinct phases before and during a knee replacement surgery. We qualitatively inspect views rendered by a virtual camera that moves 180 degrees around the surgical field at differing time values. Quantitatively, we evaluate view synthesis from an unseen camera position in terms of PSNR, SSIM and LPIPS for the colour channels and in MAE and error percentage for the estimated depth. We find that NeRFs can be used to generate geometrically consistent views, also from interpolated camera positions and at interpolated time intervals. Views are generated from an unseen camera pose with an average PSNR of 18.2 and a depth estimation error of 2.0%. Our results show the potential of a dynamic NeRF for view synthesis in the OR and stress the relevance of depth supervision in a clinical setting.

Related papers

• Redundancy-Aware Camera Selection for Indoor Scene Neural Rendering [54.468355408388675]
  We build a similarity matrix that incorporates both the spatial diversity of the cameras and the semantic variation of the images. We apply a diversity-based sampling algorithm to optimize the camera selection. We also develop a new dataset, IndoorTraj, which includes long and complex camera movements captured by humans in virtual indoor environments.
  arXiv  Detail & Related papers  (2024-09-11T08:36:49Z)
• UC-NeRF: Neural Radiance Field for Under-Calibrated Multi-view Cameras in Autonomous Driving [32.03466915786333]
  UC-NeRF is a novel method tailored for novel view synthesis in under-calibrated multi-view camera systems. We propose a layer-based color correction to rectify the color inconsistency in different image regions. Second, we propose virtual warping to generate more viewpoint-diverse but consistent views for color correction and 3D recovery.
  arXiv  Detail & Related papers  (2023-11-28T16:47:59Z)
• DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields [71.94156412354054]
  We propose Dynamic Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields (DynaMoN) DynaMoN handles dynamic content for initial camera pose estimation and statics-focused ray sampling for fast and accurate novel-view synthesis. We extensively evaluate our approach on two real-world dynamic datasets, the TUM RGB-D dataset and the BONN RGB-D Dynamic dataset.
  arXiv  Detail & Related papers  (2023-09-16T08:46:59Z)
• Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection [90.35085487641773]
  Low dynamic range (LDR) cameras cannot deal with wide dynamic range inputs, frequently leading to local overexposure issues. We present a learning-based system to reduce these artifacts without resorting to complex processing mechanisms.
  arXiv  Detail & Related papers  (2023-08-29T17:40:57Z)
• A Comparative Neural Radiance Field (NeRF) 3D Analysis of Camera Poses from HoloLens Trajectories and Structure from Motion [0.0]
  We present a workflow for high-resolution 3D reconstructions almost directly from HoloLens data using Neural Radiance Fields (NeRFs) NeRFs are trained using a set of camera poses and associated images as input to estimate density and color values for each position. Results show that the internal camera poses lead to NeRF convergence with a PSNR of 25,dB with a simple rotation around the x-axis and enable a 3D reconstruction.
  arXiv  Detail & Related papers  (2023-04-20T22:17:28Z)
• Robustifying the Multi-Scale Representation of Neural Radiance Fields [86.69338893753886]
  We present a robust multi-scale neural radiance fields representation approach to overcome both real-world imaging issues. Our method handles multi-scale imaging effects and camera-pose estimation problems with NeRF-inspired approaches. We demonstrate, with examples, that for an accurate neural representation of an object from day-to-day acquired multi-view images, it is crucial to have precise camera-pose estimates.
  arXiv  Detail & Related papers  (2022-10-09T11:46:45Z)
• CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations [77.90883737693325]
  This paper proposes CLONeR, which significantly improves upon NeRF by allowing it to model large outdoor driving scenes observed from sparse input sensor views. This is achieved by decoupling occupancy and color learning within the NeRF framework into separate Multi-Layer Perceptrons (MLPs) trained using LiDAR and camera data, respectively. In addition, this paper proposes a novel method to build differentiable 3D Occupancy Grid Maps (OGM) alongside the NeRF model, and leverage this occupancy grid for improved sampling of points along a ray for rendering in metric space.
  arXiv  Detail & Related papers  (2022-09-02T17:44:50Z)
• Ev-NeRF: Event Based Neural Radiance Field [8.78321125097048]
  Ev-NeRF is a Neural Radiance Field derived from event data. We show that Ev-NeRF achieves competitive performance for intensity image reconstruction under extreme noise conditions.
  arXiv  Detail & Related papers  (2022-06-24T18:27:30Z)
• T\"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis [32.878225196378374]
  We introduce a neural representation based on an image formation model for continuous-wave ToF cameras. We show that this approach improves robustness of dynamic scene reconstruction to erroneous calibration and large motions.
  arXiv  Detail & Related papers  (2021-09-30T17:12:59Z)
• NeRF--: Neural Radiance Fields Without Known Camera Parameters [31.01560143595185]
  This paper tackles the problem of novel view synthesis (NVS) from 2D images without known camera poses and intrinsics. We propose an end-to-end framework, termed NeRF--, for training NeRF models given only RGB images.
  arXiv  Detail & Related papers  (2021-02-14T03:52:34Z)
• iNeRF: Inverting Neural Radiance Fields for Pose Estimation [68.91325516370013]
  We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF) NeRFs have been shown to be remarkably effective for the task of view synthesis.
  arXiv  Detail & Related papers  (2020-12-10T18:36:40Z)

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.