MIVIFI: Bridging Perspective and Fisheye Domains for Training Multi-View Fisheye Image Generation Models

• URL: http://arxiv.org/abs/2608.23140v1
• Date: Mon, 24 Aug 2026 11:46:28 GMT
• Title: MIVIFI: Bridging Perspective and Fisheye Domains for Training Multi-View Fisheye Image Generation Models
• Abstract summary: Fisheye cameras offer a cost-effective solution by enabling full surround coverage with as few as two sensors.<n>Existing multi-view fisheye datasets are limited, and rare corner cases typically require computationally expensive 3D simulations.<n>We present two distinct methods for generating multi-view fisheye images conditioned on volumetric semantic representations.
• Score: 44.93230202195852
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Achieving 360° coverage is critical for the visual perception systems of autonomous vehicles. Fisheye cameras offer a cost-effective solution by enabling full surround coverage with as few as two sensors. However, existing multi-view fisheye datasets are limited, and synthesizing rare corner cases typically requires computationally expensive 3D simulations, hindering the training. While generative models have achieved significant success in standard perspective imagery, their application to wide-angle distortion remains unexplored. In this work, we formally introduce the novel problem of multi-view fisheye image generation conditioned on volumetric semantic representations and present two distinct methods. We first propose SyntheOcc-FE, which adapts the SyntheOcc architecture to fisheye data. While effective, this method is constrained by the scarcity of fisheye datasets, which limits its generalization. To overcome these limitations, we propose our second method, MIVIFI (multi-view fisheye), which leverages cross-domain learning with Equirectangular Projections. By bridging the gap between dataset domains using KITTI-360 fisheye images alongside nuScenes multi-view standard images, our approach enables high-fidelity manipulation of scene content. This framework enables the structural modification of semantic occupancy inputs to introduce or eliminate specific actors and facilitates the rendering of diverse meteorological conditions and illumination scenarios absent in the limited fisheye datasets. Quantitative and qualitative experiments demonstrate that our methods achieve robust photorealistic multi-view fisheye image generation and highlight the specific advantages of our cross-domain strategy for handling data scarcity.

Related papers

• From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation [6.335915125785494]
  We propose a method to generalize vision foundation models to fisheye cameras.<n>The crux of our method lies in a set of learnable parameters, termed Distortion Extenders (DEX)<n>DEX transforms the latent embeddings of fisheye images to resemble those of perspective images to recover high-fidelity estimates.
  arXiv  Detail & Related papers  (2026-08-28T03:10:18Z)
• DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization [17.91043282211744]
  3D Gaussian Splatting (3DGS) has enabled efficient 3D scene reconstruction from everyday images with real-time, high-fidelity rendering.<n>Fisheye cameras, with their wider field of view (FOV), promise high-quality reconstructions from fewer inputs.
  arXiv  Detail & Related papers  (2026-04-01T09:00:04Z)
• Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses [5.987299558427844]
  Fisheye3R is a novel adaptation framework that extends multi-view 3D reconstruction foundation models to accommodate fisheye inputs without performance regression on perspective images.<n>Our approach consistently improves camera pose, depth, point map, and field-of-view estimation on fisheye images.
  arXiv  Detail & Related papers  (2026-03-30T18:18:56Z)
• Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery [51.73680703579997]
  We present a neural radiance field method for urban-scale semantic and building-level instance segmentation from aerial images. objects in urban aerial images exhibit substantial variations in size, including buildings, cars, and roads. We introduce a scale-adaptive semantic label fusion strategy that enhances the segmentation of objects of varying sizes. We then introduce a novel cross-view instance label grouping strategy to mitigate the multi-view inconsistency problem in the 2D instance labels.
  arXiv  Detail & Related papers  (2024-03-18T14:15:39Z)
• Exposure Bracketing Is All You Need For A High-Quality Image [50.822601495422916]
  Multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution.<n>We propose to utilize exposure bracketing photography to get a high-quality image by combining these tasks in this work.<n>In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed.
  arXiv  Detail & Related papers  (2024-01-01T14:14:35Z)
• SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning [105.01294305972037]
  We introduce SimFIR, a framework for fisheye image rectification based on self-supervised representation learning. To learn fine-grained distortion representations, we first split a fisheye image into multiple patches and extract their representations with a Vision Transformer. The transfer performance on the downstream rectification task is remarkably boosted, which verifies the effectiveness of the learned representations.
  arXiv  Detail & Related papers  (2023-08-17T15:20:17Z)
• FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation [33.71849096992972]
  This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV) We introduce the new FishDreamer which relies on successful ViTs enhanced with a novel Polar-aware Cross Attention module (PCA) to leverage dense context and guide semantically-consistent content generation.
  arXiv  Detail & Related papers  (2023-03-24T07:34:25Z)
• Gait Recognition in Large-scale Free Environment via Single LiDAR [35.684257181154905]
  LiDAR's ability to capture depth makes it pivotal for robotic perception and holds promise for real-world gait recognition. We present the Hierarchical Multi-representation Feature Interaction Network (HMRNet) for robust gait recognition. To facilitate LiDAR-based gait recognition research, we introduce FreeGait, a comprehensive gait dataset from large-scale, unconstrained settings.
  arXiv  Detail & Related papers  (2022-11-22T16:05:58Z)
• MC-Blur: A Comprehensive Benchmark for Image Deblurring [127.6301230023318]
  In most real-world images, blur is caused by different factors, e.g., motion and defocus. We construct a new large-scale multi-cause image deblurring dataset (called MC-Blur) Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios.
  arXiv  Detail & Related papers  (2021-12-01T02:10:42Z)
• Self-Supervised Multi-Frame Monocular Scene Flow [61.588808225321735]
  We introduce a multi-frame monocular scene flow network based on self-supervised learning. We observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.
  arXiv  Detail & Related papers  (2021-05-05T17:49:55Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)
• SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images [15.573003283204958]
  We present a novel framework for adapting a ROI-based 6D object pose estimation method to work on full fisheye images. We also contribute a fisheye image dataset, called UWHandles, with 6D object pose and 2D bounding box annotations.
  arXiv  Detail & Related papers  (2020-02-27T19:57:33Z)

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.