1
2
Visual enhancement and 3D representation for underwater scenes: a review
系统梳理水下场景视觉增强与三维表示的近五年研究进展，涵盖成像退化、深度估计与重建方法，适合相关领域研究者快速把握学术脉络。
arXiv:2505.01869v2 Announce Type: replace Abstract: Underwater visual enhancement (UVE) and underwater 3D reconstruction pose significant challenges i…
3
Leveraging Metric Depth for Relative Depth Prediction
利用预训练模型零样本能力，解决足球场景下训练样本少的单目深度估计难题，方法新颖且实用。
arXiv:2606.10628v1 Announce Type: new Abstract: We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predic…
4
DenseMLLM: Standard Multimodal LLMs for Dense Prediction
标准多模态大模型如何突破粗粒度限制，实现像素级稠密预测任务。
arXiv:2602.14134v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-…
5
Unlocking Dense Metric Depth Estimation in VLMs
新型方法让视觉语言模型突破3D密集几何感知瓶颈，实现高效深度估计。
arXiv:2605.15876v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited i…