quiet-sleep
发表于 2025-3-30 12:09:22
,High-Precision Self-supervised Monocular Depth Estimation with Rich-Resource Prior,ypically achieve better performance than models that use ordinary single image input. However, these rich-resource inputs may not always be available, limiting the applicability of these methods in general scenarios. In this paper, we propose Rich-resource Prior Depth estimator (RPrDepth), which onl
Connotation
发表于 2025-3-30 14:26:47
http://reply.papertrans.cn/25/2424/242327/242327_52.png
拥挤前
发表于 2025-3-30 20:24:55
http://reply.papertrans.cn/25/2424/242327/242327_53.png
不爱防注射
发表于 2025-3-30 20:41:09
OmniSSR: Zero-Shot Omnidirectional Image Super-Resolution Using Stable Diffusion Model,sks. Most existing super-resolution methods for ODIs use end-to-end learning strategies, resulting in inferior realness of generated images and a lack of effective out-of-domain generalization capabilities in training methods. Image generation methods represented by diffusion model provide strong pr
证明无罪
发表于 2025-3-31 01:26:24
,UDiffText: A Unified Framework for High-Quality Text Synthesis in Arbitrary Images via Character-Awods produce visually appealing results, they frequently exhibit spelling errors when rendering text within the generated images. Such errors manifest as missing, incorrect or extraneous characters, thereby severely constraining the performance of text image generation based on diffusion models. To a
BULLY
发表于 2025-3-31 06:35:32
,Confidence Self-calibration for Multi-label Class-Incremental Learning, and future labels remain unavailable. This issue leads to a proliferation of false-positive errors due to erroneously high confidence multi-label predictions, exacerbating catastrophic forgetting within the disjoint label space. In this paper, we aim to refine multi-label confidence calibration in
Goblet-Cells
发表于 2025-3-31 10:14:24
,OMG: Occlusion-Friendly Personalized Multi-concept Generation in Diffusion Models,hods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlusion-friendly personalized generation framework designed to seamlessly integrate multiple concepts within a single image. We propose a novel two-stage s
installment
发表于 2025-3-31 16:09:09
,Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning,ally assume that an incoming task has only increments of classes or domains, referred to as Class IL (CIL) or Domain IL (DIL), respectively. In this work, we consider a more challenging and realistic but under-explored IL scenario, named ., in which a model has no prior of which of the classes or do
射手座
发表于 2025-3-31 19:45:46
,WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-Only Supervised Timinating expensive boundary annotation. The crux of this task lies in locating each transcription in scene text images without location annotations. In this work, we formulate this challenging problem as a .akly Supervised .ss-.odality .ontrastive .earning problem, and design a simple yet effective
PATRI
发表于 2025-3-31 23:50:19
,An Incremental Unified Framework for Small Defect Inspection,ned for specific industrial products and struggle with diverse product portfolios and evolving processes. Although some previous studies attempt to address object dynamics by storing embeddings in the reserved memory bank, these methods suffer from memory capacity limitations and object distribution