Nowadays superpixel algorithms are widely used in computer vision and computer graphics applications. However existing algorithms are designed for planar images, which are less suited to deal with wide angle images. In this paper, we present a superpixel segmentation method for 360° spherical images. Unlike previous methods, our approach explicitly considers the geometry for spherical images and makes clustering to spherical image pixels. It starts with the seeds defined by Hammersley points sampled on the sphere, then iterates between assignment step and update step which are both based on the distance metric respecting spherical geometry. We evaluate our method on the transformed Berkeley segmentation dataset and panorama segmentation dataset collected by ourselves. Experimental results show that our method can get better performance in terms of adherence to image boundaries and superpixel structural regularity. Furthermore, superpixels generated by our method can reserve the coherence across image boundaries and all have closed contours.

This paper investigates the challenges of UAV-view geo-localization under extreme environmental changes, where significant cross-domain style differences can lead to degradation of model performance. Existing methods primarily focus on mitigating domain shift issues caused by environmental factors but generally overlook the direct interference of environmental noise. We argue that mitigating environmental noise is equally critical for extracting discriminative cross-view features and introduce a pixel-to-feature co-enhancement network (P2FCN). P2FCN comprises a style-noise dual suppression module (SNDS) and a part-based multi-dimensional feature learning strategy (PMDFL). Specifically, the SNDS module mitigates the stylistic discrepancies between cross-environment images through pixel-level dynamic adjustment, while reducing the introduction of environmental noise to a certain degree. PMDFL improves the representation generalization by purifying discriminative information within partitioned channel-and spatial-wise feature subspaces. Extensive experiments on two widely used benchmarks, i.e., University-1652 and SUES-200, demonstrate that the proposed method achieves state-of-the-art performance in multiple environments compared to existing methods.

In this technical report, we represent our solution for the ACMMM24 Multimedia Drone Satellite Matching Challenge in Multiple Environment. Our solution targets at learning discriminative descriptors to cope with the environmental changes when aerial-view geo-localization in open scenarios. Specifically, our network is based on the square-ring partition and employs ConvNeXt with the stride of the last down-sample layer set to 1 as the backbone to extract richer fine-grained information. In addition, since drone-view images contain environmental distraction, we adopt two loss functions to strengthen the optimization constraints on the designed network. Experiments show that our method can effectively match multi-environment drone-view images with satellite images and achieve competitive accuracy on University160k-WX.

Camera-based Bird's-Eye-View (BEV) representation has become a viable solution for 3D object detection in cost-effective autonomous driving. Currently, the explicit paradigm based on the lift-splat-shoot (LSS) pipeline has become one of the mainstream methods due to its efficiency and ease of deployment. However, the process of flattening the spatial representation in this pipeline mixes target features with excessive background noise. In addition, the generated BEV features are sparse due to the inherent characteristics of camera imaging. To address these limitations, we propose IAE-BEV, a novel two-stage multi-view 3D object detector that adaptively integrates instance features into BEV features, ultimately constructing a BEV representation that highlights instance information and alleviates sparsity. We also introduce the Occupancy Mask Pool, which enables instance features to interact with the 2D image plane in a more targeted and efficient manner. To further distinguish instances along the same camera ray, we design the Angle-Adaptive Self-Attention, which learns appropriate feature weights under the guidance of queries. Extensive experiments on the nuScenes dataset demonstrate the effectiveness and generalizability of our proposed framework, achieving up to +2.96% mAP improvement over state-of-the-art LSS-based baseline.