SaENeRF: Suppressing Artifacts in Event-based Neural Radiance Fields

• URL: http://arxiv.org/abs/2504.16389v1
• Date: Wed, 23 Apr 2025 03:33:20 GMT
• Title: SaENeRF: Suppressing Artifacts in Event-based Neural Radiance Fields
• Authors: Yuanjian Wang, Yufei Deng, Rong Xiao, Jiahao Fan, Chenwei Tang, Deng Xiong, Jiancheng Lv,
• Abstract summary: Event cameras offer advantages such as low latency, low power consumption, low bandwidth, and high dynamic range.<n>Reconstructing geometrically consistent and photometrically accurate 3D representations from event data remains fundamentally challenging.<n>We present SaENeRF, a novel self-supervised framework that effectively suppresses artifacts and enables 3D-consistent, dense radiance, and photorealistic NeRF reconstruction of static scenes solely from event streams.
• Score: 12.428456822446947
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Event cameras are neuromorphic vision sensors that asynchronously capture changes in logarithmic brightness changes, offering significant advantages such as low latency, low power consumption, low bandwidth, and high dynamic range. While these characteristics make them ideal for high-speed scenarios, reconstructing geometrically consistent and photometrically accurate 3D representations from event data remains fundamentally challenging. Current event-based Neural Radiance Fields (NeRF) methods partially address these challenges but suffer from persistent artifacts caused by aggressive network learning in early stages and the inherent noise of event cameras. To overcome these limitations, we present SaENeRF, a novel self-supervised framework that effectively suppresses artifacts and enables 3D-consistent, dense, and photorealistic NeRF reconstruction of static scenes solely from event streams. Our approach normalizes predicted radiance variations based on accumulated event polarities, facilitating progressive and rapid learning for scene representation construction. Additionally, we introduce regularization losses specifically designed to suppress artifacts in regions where photometric changes fall below the event threshold and simultaneously enhance the light intensity difference of non-zero events, thereby improving the visual fidelity of the reconstructed scene. Extensive qualitative and quantitative experiments demonstrate that our method significantly reduces artifacts and achieves superior reconstruction quality compared to existing methods. The code is available at https://github.com/Mr-firework/SaENeRF.

Related papers

• Low-Light Image Enhancement using Event-Based Illumination Estimation [83.81648559951684]
  Low-light image enhancement (LLIE) aims to improve the visibility of images captured in poorly lit environments. This paper opens a new avenue from the perspective of estimating the illumination using ''temporal-mapping'' events. We construct a beam-splitter setup and collect EvLowLight dataset that includes images, temporal-mapping events, and motion events.
  arXiv  Detail & Related papers  (2025-04-13T00:01:33Z)
• AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene [31.142207770861457]
  We propose AE-NeRF to address the challenges of learning event-based NeRF from non-ideal conditions.<n>Our method achieves a new state-of-the-art in event-based 3D reconstruction.
  arXiv  Detail & Related papers  (2025-01-06T07:00:22Z)
• Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment [23.15130387716121]
  We propose Bundle Adjustment for Deblurring Neural Radiance Fields (EBAD-NeRF) to jointly optimize the learnable poses and NeRF parameters. EBAD-NeRF can obtain accurate camera trajectory during the exposure time and learn a sharper 3D representations compared to prior works.
  arXiv  Detail & Related papers  (2024-06-20T14:33:51Z)
• Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion [54.197343533492486]
  Event3DGS can reconstruct high-fidelity 3D structure and appearance under high-speed egomotion. Experiments on multiple synthetic and real-world datasets demonstrate the superiority of Event3DGS compared with existing event-based dense 3D scene reconstruction frameworks. Our framework also allows one to incorporate a few motion-blurred frame-based measurements into the reconstruction process to further improve appearance fidelity without loss of structural accuracy.
  arXiv  Detail & Related papers  (2024-06-05T06:06:03Z)
• NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild [55.154625718222995]
  We introduce NeRF On-the-go, a simple yet effective approach that enables the robust synthesis of novel views in complex, in-the-wild scenes. Our method demonstrates a significant improvement over state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-05-29T02:53:40Z)
• Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion [67.15935067326662]
  Event cameras offer low power, low latency, high temporal resolution and high dynamic range. NeRF is seen as the leading candidate for efficient and effective scene representation. We propose Robust e-NeRF, a novel method to directly and robustly reconstruct NeRFs from moving event cameras.
  arXiv  Detail & Related papers  (2023-09-15T17:52:08Z)
• Deformable Neural Radiance Fields using RGB and Event Cameras [65.40527279809474]
  We develop a novel method to model the deformable neural radiance fields using RGB and event cameras. The proposed method uses the asynchronous stream of events and sparse RGB frames. Experiments conducted on both realistically rendered graphics and real-world datasets demonstrate a significant benefit of the proposed method.
  arXiv  Detail & Related papers  (2023-09-15T14:19:36Z)
• E-NeRF: Neural Radiance Fields from a Moving Event Camera [83.91656576631031]
  Estimating neural radiance fields (NeRFs) from ideal images has been extensively studied in the computer vision community. We present E-NeRF, the first method which estimates a volumetric scene representation in the form of a NeRF from a fast-moving event camera.
  arXiv  Detail & Related papers  (2022-08-24T04:53:32Z)
• EventNeRF: Neural Radiance Fields from a Single Colour Event Camera [81.19234142730326]
  This paper proposes the first approach for 3D-consistent, dense and novel view synthesis using just a single colour event stream as input. At its core is a neural radiance field trained entirely in a self-supervised manner from events while preserving the original resolution of the colour event channels. We evaluate our method qualitatively and numerically on several challenging synthetic and real scenes and show that it produces significantly denser and more visually appealing renderings.
  arXiv  Detail & Related papers  (2022-06-23T17:59:53Z)
• 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)

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.