Snap Angle Prediction for 360$^{\circ}$ Panoramas

2018-03-31 · Bo Xiong, Kristen Grauman

360$^{\circ}$ panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible distortions. Whereas existing approaches assume the viewpoint is fixed, intuitively some viewing angles within the sphere preserve high-level objects better than others. To discover the relationship between these optimal snap angles and the spherical panorama's content, we develop a reinforcement learning approach for the cubemap projection model. Implemented as a deep recurrent neural network, our method selects a sequence of rotation actions and receives reward for avoiding cube boundaries that overlap with important foreground objects. We show our approach creates more visually pleasing panoramas while using 5x less computation than the baseline.

📄 PDF Abstract BibTeX arXiv:1804.00126

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Snap Angle Prediction for 360Â° Panoramas

2018-09-01 · ECCV 2018 9 · Bo Xiong, Kristen Grauman

360Â° panoramas are a rich medium, yet notoriously difficult to visualize in the 2D image plane. We explore how intelligent rotations of a spherical image may enable content-aware projection with fewer perceptible disto…

Prediction reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

360-Degree Panorama Generation from Few Unregistered NFoV Images

2023-08-28 · Jionghao Wang, Ziyu Chen, Jun Ling, Rong Xie 외

360$^\circ$ panoramas are extensively utilized as environmental light sources in computer graphics. However, capturing a 360$^\circ$ $\times$ 180$^\circ$ panorama poses challenges due to the necessity of specialized and …

SE360: Semantic Edit in 360$^\circ$ Panoramas via Hierarchical Data Construction

2025-12-23 · Haoyi Zhong, Fang-Lue Zhang, Andrew Chalmers, Taehyun Rhee arxiv

While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and …

Image Editing

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

2023-06-02 · NeurIPS 2023 11 · Zheng Chen, Yan-Pei Cao, Yuan-Chen Guo, Chen Wang 외

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly…

Depth Estimation

Deep Multi Depth Panoramas for View Synthesis

2020-08-04 · ECCV 2020 8 · Kai-En Lin, Zexiang Xu, Ben Mildenhall, Pratul P. Srinivasan 외

We propose a learning-based approach for novel view synthesis for multi-camera 360$^{\circ}$ panorama capture rigs. Previous work constructs RGBD panoramas from such data, allowing for view synthesis with small amounts o…

Novel View Synthesis Translation