360Recon: An Accurate Reconstruction Method Based on Depth Fusion from 360 Images
360-degree images offer a significantly wider field of view compared to traditional pinhole cameras, enabling sparse sampling and dense 3D reconstruction in low-texture environments. This makes them crucial for applications in VR, AR, and related fields. However, the inherent distortion caused by the wide field of view affects feature extraction and matching, leading to geometric consistency issues in subsequent multi-view reconstruction. In this work, we propose 360Recon, an innovative MVS algorithm for ERP images. The proposed spherical feature extraction module effectively mitigates distortion effects, and by combining the constructed 3D cost volume with multi-scale enhanced features from ERP images, our approach achieves high-precision scene reconstruction while preserving local geometric consistency. Experimental results demonstrate that 360Recon achieves state-of-the-art performance and high efficiency in depth estimation and 3D reconstruction on existing public panoramic reconstruction datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionDepth EstimationERPSimilar Papers 제목 키워드 기반
SimpleRecon: 3D Reconstruction Without 3D Convolutions
Traditionally, 3D indoor scene reconstruction from posed images happens in two phases: per-image depth estimation, followed by depth merging and surface reconstruction. Recently, a family of methods have emerged that per…
3D ReconstructionDepth EstimationDepth PredictionIndoor Scene Reconstruction+1Differentiable Diffusion for Dense Depth Estimation from Multi-view Images
We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, dep…
Depth EstimationEndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completion
Accurate depth estimation plays a critical role in the navigation of endoscopic surgical robots, forming the foundation for 3D reconstruction and safe instrument guidance. Fine-tuning pretrained models heavily relies on …
3D ReconstructionDepth EstimationDepth CompletionPerspective-aware fusion of incomplete depth maps and surface normals for accurate 3D reconstruction
We address the problem of reconstructing 3D surfaces from depth and surface normal maps acquired by a sensor system based on a single perspective camera. Depth and normal maps can be obtained through techniques such as s…
3D ReconstructionPixel-Aligned Multi-View Generation with Depth Guided Decoder
The task of image-to-multi-view generation refers to generating novel views of an instance from a single image. Recent methods achieve this by extending text-to-image latent diffusion models to multi-view version, which …
3D ReconstructionDecoderDepth Estimation