SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
- URL: http://arxiv.org/abs/2502.05859v1
- Date: Sun, 09 Feb 2025 11:36:45 GMT
- Title: SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
- Authors: Qingsong Yan, Qiang Wang, Kaiyong Zhao, Jie Chen, Bo Li, Xiaowen Chu, Fei Deng,
- Abstract summary: We present SphereFusion, an end-to-end framework that combines the strengths of various projection methods.
Specifically, SphereFusion employs 2D image convolution and mesh operations to extract two types of features from the panorama image in both equirectangular and spherical projection domains.
We show that SphereFusion achieves competitive results with other state-of-the-art methods, while presenting the fastest inference speed at only 17 ms on a 512$times$1024 panorama image.
- Score: 21.97835451388508
- License:
- Abstract: Due to the rapid development of panorama cameras, the task of estimating panorama depth has attracted significant attention from the computer vision community, especially in applications such as robot sensing and autonomous driving. However, existing methods relying on different projection formats often encounter challenges, either struggling with distortion and discontinuity in the case of equirectangular, cubemap, and tangent projections, or experiencing a loss of texture details with the spherical projection. To tackle these concerns, we present SphereFusion, an end-to-end framework that combines the strengths of various projection methods. Specifically, SphereFusion initially employs 2D image convolution and mesh operations to extract two distinct types of features from the panorama image in both equirectangular and spherical projection domains. These features are then projected onto the spherical domain, where a gate fusion module selects the most reliable features for fusion. Finally, SphereFusion estimates panorama depth within the spherical domain. Meanwhile, SphereFusion employs a cache strategy to improve the efficiency of mesh operation. Extensive experiments on three public panorama datasets demonstrate that SphereFusion achieves competitive results with other state-of-the-art methods, while presenting the fastest inference speed at only 17 ms on a 512$\times$1024 panorama image.
Related papers
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion [60.45000652592418]
We propose a novel text-driven panoramic generation framework, DiffPano, to achieve scalable, consistent, and diverse panoramic scene generation.
We show that DiffPano can generate consistent, diverse panoramic images with given unseen text descriptions and camera poses.
arXiv Detail & Related papers (2024-10-31T17:57:02Z) - SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model [63.685132323224124]
Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.
In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges.
Experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
arXiv Detail & Related papers (2024-03-15T06:26:46Z) - Curved Diffusion: A Generative Model With Optical Geometry Control [56.24220665691974]
The influence of different optical systems on the final scene appearance is frequently overlooked.
This study introduces a framework that intimately integrates a textto-image diffusion model with the particular lens used in image rendering.
arXiv Detail & Related papers (2023-11-29T13:06:48Z) - Multi-Projection Fusion and Refinement Network for Salient Object
Detection in 360{\deg} Omnidirectional Image [141.10227079090419]
We propose a Multi-Projection Fusion and Refinement Network (MPFR-Net) to detect the salient objects in 360deg omnidirectional image.
MPFR-Net uses the equirectangular projection image and four corresponding cube-unfolding images as inputs.
Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.
arXiv Detail & Related papers (2022-12-23T14:50:40Z) - BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360
Depth Estimation [59.11106101006008]
We propose BiFuse++ to explore the combination of bi-projection fusion and the self-training scenario.
We propose a new fusion module and Contrast-Aware Photometric Loss to improve the performance of BiFuse.
arXiv Detail & Related papers (2022-09-07T06:24:21Z) - SphereDepth: Panorama Depth Estimation from Spherical Domain [17.98608948955211]
This paper proposes SphereDepth, a novel panorama depth estimation method.
It predicts the depth directly on the spherical mesh without projection preprocessing.
It achieves comparable results with the state-of-the-art methods of panorama depth estimation.
arXiv Detail & Related papers (2022-08-29T16:50:19Z) - PanoFormer: Panorama Transformer for Indoor 360{\deg} Depth Estimation [35.698249161263966]
Existing panoramic depth estimation methods based on convolutional neural networks (CNNs) focus on removing panoramic distortions.
This paper proposes the panorama transformer (named PanoFormer) to estimate the depth in panorama images.
In particular, we divide patches on the spherical tangent domain into tokens to reduce the negative effect of panoramic distortions.
arXiv Detail & Related papers (2022-03-17T12:19:43Z) - ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama
Depth Estimation [9.670696363730329]
We propose an ACDNet based on the adaptively combined dilated convolution to predict the dense depth map for a monocular panoramic image.
We conduct depth estimation experiments on three datasets (both virtual and real-world) and the experimental results demonstrate that our proposed ACDNet substantially outperforms the current state-of-the-art (SOTA) methods.
arXiv Detail & Related papers (2021-12-29T08:04:19Z) - EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation [62.210091681352914]
We study multi-sensor fusion for 3D semantic segmentation for many applications, such as autonomous driving and robotics.
In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF)
We propose a two-stream network to extract features from the two modalities separately. The extracted features are fused by effective residual-based fusion modules.
arXiv Detail & Related papers (2021-06-21T10:47:26Z) - UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth
Estimation [11.680475784102308]
This paper introduces a new framework to fuse features from the two projections, unidirectionally feeding the cubemap features to the equirectangular features only at the decoding stage.
Experiments verify the effectiveness of our proposed fusion strategy and module, and our model achieves state-of-the-art performance on four popular datasets.
arXiv Detail & Related papers (2021-02-06T10:01:09Z) - Distortion-aware Monocular Depth Estimation for Omnidirectional Images [26.027353545874522]
We propose a Distortion-Aware Monocular Omnidirectional (DAMO) dense depth estimation network to address this challenge on indoor panoramas.
First, we introduce a distortion-aware module to extract calibrated semantic features from omnidirectional images.
Second, we introduce a plug-and-play spherical-aware weight matrix for our objective function to handle the uneven distribution of areas projected from a sphere.
arXiv Detail & Related papers (2020-10-18T08:47:57Z)
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.