3D edge reconstruction from posed multi-view images remains a critical yet under-explored task. While 3D Gaussian Splatting (3DGS)-based methods have recently achieved promising performance, they face two main challenges. First, edges exhibit clear discontinuities from the background, but the intrinsic smoothness of Gaussian kernels makes it challenging to model such discontinuities. Second, due to the absence of multi-view edge annotations, models are trained with pseudo labels instead. These pseudo labels extracted by pre-trained$2 D$edge detectors often exhibit cross-view inconsistencies, leading to degraded performance. To address these issues, we propose a novel uncertainty-aware 3D edge reconstruction using Difference of Gaussians (DoG) as kernels, called EdgeDoG. First, we incorporate DoG kernels to model edge discontinuities explicitly. Second, we design a dual-uncertainty strategy: primitive-level uncertainty is estimated via multi-view Fisher information to eliminate noisy 3D primitives, while pixel-level uncertainty is computed from gradients of rendered depth maps to reweight the training loss, thereby compensating for inconsistent 2D pseudo labels with robust 3D geometric cues. Extensive experiments on diverse datasets demonstrate that our method achieves superior performance compared to previous approaches.

Medical image segmentation is highly challenging due to the uncertainties caused by the inherent ambiguous regions and expert knowledge variations. Some recent works explore the uncertainties and produce multiple outputs to obtain more robust results. However, the quality of the boundary areas remains unsatisfactory. Unfortunately, the key differences among experts usually lie in these boundary areas, which are more critical in practical diagnosis. To tackle the above issues, different from previous pixel-wise segmentation approaches, we present a new perspective and formulate the task as a contour-based regression problem, and further propose a novel Contour-aware Multi-expert Segmentor, named ContourMS, which can provide diverse segmentation results with rich boundary details in a coarse-to-fine manner. Specifically, in the coarse stage, we use a SegmentNet to predict a region mask by leveraging the knowledge of multiple experts, and then the mask is converted to an initial contour shared by all experts. In the fine stage, we design a LatentNet to learn the expert-level latent space and a ContourNet to refine each expert contour, where the deformation guided by the expert style can gradually adjust the contour to match different annotations. Extensive experiments demonstrate that the proposed method can generate diverse segment variants and achieve competitive performance on multiple public multi-expert medical segmentation datasets.

Edge segmentation is well-known to be subjective due to personalized annotation styles and preferred granular-ity. However, most existing deterministic edge detection methods produce only a single edge map for one input image. We argue that generating multiple edge maps is more reasonable than generating a single one considering the subjectivity and ambiguity of the edges. Thus motivated, in this paper we propose multiple granularity edge detection, called MuGE, which can produce a wide range of edge maps, from approximate object contours to fine texture edges. Specifically, we first propose to design an edge granularity network to estimate the edge granularity from an individual edge annotation. Subsequently, to guide the generation of diversified edge maps, we integrate such edge granularity into the multi-scale feature maps in the spatial domain. Meanwhile, we decompose the feature maps into low-frequency and high-frequency parts, where the encoded edge granularity is further fused into the high-frequency part to achieve more precise control over the details of the produced edge maps. Compared to previous methods, MuGE is able to not only generate multiple edge maps at different controllable granularities but also achieve a com-petitive performance on the BSDS500 and Multicue benchmark datasets.

Semantic edge detection (SED) is pivotal for the precise demarcation of object boundaries, yet it faces ongoing challenges due to the prevalence of low-quality labels in current methods. In this paper, we present a novel solution to bolster SED through the encoding of both language and image data. Distinct from antecedent language-driven techniques, which predominantly utilize static elements such as dataset labels, our method taps into the dynamic language content that details the objects in each image and their interrelations. By encoding this varied input, we generate integrated features that utilize semantic insights to refine the high-level image features and the ultimate mask representations. This advancement improves the quality of these features and elevates SED performance. Experimental evaluation on benchmark datasets, including SBD and Cityscape, showcases the efficacy of our method, achieving leading ODS F-scores of 79.0 and 76.0, respectively. Our approach signifies a notable advancement in SED technology by seamlessly integrating multimodal textual information, embracing both static and dynamic aspects.

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators. Existing methods fuse multiple annotations using a simple voting process, ignoring the inherent ambiguity of edges and labeling bias of annotators. In this paper, we propose a novel uncertainty-aware edge detector (UAED), which employs uncertainty to investigate the subjectivity and ambiguity of diverse annotations. Specifically, we first convert the deterministic label space into a learnable Gaussian distribution, whose variance measures the degree of ambiguity among different annotations. Then we regard the learned variance as the estimated uncertainty of the predicted edge maps, and pixels with higher uncertainty are likely to be hard samples for edge detection. Therefore we design an adaptive weighting loss to emphasize the learning from those pixels with high uncertainty, which helps the network to gradually concentrate on the important pixels. UAED can be combined with various encoder-decoder backbones, and the extensive experiments demonstrate that UAED achieves superior performance consistently across multiple edge detection benchmarks. The source code is available at https://github.com/ZhouCX117/UAED.