arXiv Computer Vision October 19, 2026 By Chengyang Zhang, Zhihao Wang, Zhiyu Long, Xueqian Wang, Quanming Yao, Wei Wu, Gang Li

FloodVLM-Pix: Language-Guided Pixel-Level Flood Understanding

Read the original on arXiv Computer Vision →

FloodVLM-Pix is a new language‑guided pixel‑level flood understanding model introduced in the arXiv paper "FloodVLM-Pix: Language‑Guided Pixel‑Level Flood Understanding." The authors created the first large‑scale remote sensing flood multi‑modal benchmark, comprising 131,200 image patches and 443,100 textual descriptions of flood severity and evolution. FloodVLM‑Pix incorporates a flood prior module to mitigate attentional bias and a multi‑temporal flood pixel decoder with a general‑specific feature fusion mechanism to improve flood segmentation accuracy. "whyItMatters":"The paper presents a benchmark and model that enhance both flood description quality and pixel‑level segmentation, addressing shortcomings of existing vision‑language models on flood‑related tasks."

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers

Jun 23

Flood Mapping from RGB imagery using a Vision Foundation Model

Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for flood mapping as it can be collected rapidly at low cost.

llms computer-vision fine-tuning benchmarks

arXiv AI

Aug 18

FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge

arXiv:2608. 15410v1 Announce Type: cross Abstract: Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents.

By Rajat Bhattacharjya, Yoomee Jung, Minwoo Kim, Sing-Yao Wu, Eli Bozorgzadeh, Nalini Venkatasubramanian, Nikil Dutt

llms agents computer-vision robotics multimodal benchmarks

arXiv Computer Vision

Sep 16

From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation

arXiv:2505.15147v3 Announce Type: replace Abstract: Remote sensing images (RSIs) capture both natural and human-induced changes on the Earth's surface. Semantic segmentation (SS) of RSIs enables the...

By Quanwei Liu, Tao Huang, Jiaqi Yang, Wei Xiang

computer-vision multimodal

arXiv Machine Learning

Aug 11

Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation

arXiv:2608. 07562v1 Announce Type: cross Abstract: Urban flooding poses an escalating threat to transportation infrastructure, yet no operational system provides real-time, street-level flood-depth estimates at centimeter resolution.

By Nafis Fuad, Xiaodong Qian, Dongxiao Zhu

llms computer-vision fine-tuning multimodal benchmarks safety

arXiv AI

Jun 18

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

arXiv:2606. 18661v1 Announce Type: cross Abstract: Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual limitations and domain hallucinations in complex geological scenarios.

By Chengfu Liu, Dongyang Hou, Junwu Xiang, Cheng Yang, Xuezhi Cui, Zeyuan Wang, Liangtian Liu, Zelang Miao

llms agents computer-vision fine-tuning multimodal safety

arXiv AI

Sep 10

Knowledge-Guided Vision-Language Inference for Image-Based Urban Flood Depth Estimation

The paper introduces FloodVision, a knowledge-guided vision‑language framework that estimates urban flood depth from a single RGB image. It combines a general‑purpose vision‑language model with FloodKG, a domain knowledge base that encodes canonical object dimensions and component landmarks to promote component‑level reasoning. On 654 crowdsourced New York flood images, FloodVision cuts mean absolute error from 15.62 cm to 8.75 cm and median error from 14.35 cm to 7.75 cm, outperforming the VLM‑only baseline in 69.3 % of cases.

By Zhangding Liu, Neda Mohammadi, John E. Taylor

llms rag computer-vision multimodal

One email a morning, machine-written

Related stories

Flood Mapping from RGB imagery using a Vision Foundation Model

FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge

From Pixels to Images: A Structural Survey of Deep Learning Paradigms in Remote Sensing Image Semantic Segmentation

Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

Knowledge-Guided Vision-Language Inference for Image-Based Urban Flood Depth Estimation