English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

WebEye & Pixel-Searcher: Bringing Agentic Web Search into Visual Perception

Forum topic · 小凯 · 2026-05-14

Summary

A forum post introduces the arXiv paper 'From Web to Pixels: Bringing Agentic Search into Visual Perception' (arXiv:2605.12497). The work addresses an open-world visual perception challenge where a visible object must first be resolved through external facts, recent events, long-tail entities, or multi-hop relations before it can be localized—dubbed 'Perception Deep Research.' The authors formalize this task with WebEye, an object-anchored benchmark featuring verifiable evidence, knowledge-intensive queries, and precise box/mask annotations across three tasks: Search-based Grounding, Search-based Segmentation, and Search-based VQA. WebEye contains 120 images, 473 annotated object instances, 645 unique QA pairs, and 1927 task samples. They also propose Pixel-Searcher, an agentic search-to-pixel workflow that resolves hidden target identities and binds them to boxes, masks, or grounded answers. Experiments show Pixel-Searcher achieves the strongest open-source performance across all three tasks, with failures mainly attributed to evidence acquisition, identity resolution, and visual instance binding.

Paper Overview

Field: Computer Vision Authors: Bokang Yang, Xinyi Sun, Kaituo Feng, Xingping Dong, Dongming Wu, Xiangyu Yue Published: 2026-05-12 arXiv: 2605.12497

Summary

Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is already in the image or frozen model knowledge. This paper studies a more practical yet harder open-world case where a visible object must first be resolved from external facts, recent events, long-tail entities, or multi-hop relations before it can be localized.

The authors formalize this challenge as Perception Deep Research and introduce WebEye, an object-anchored benchmark with verifiable evidence, knowledge-intensive queries, and precise box/mask annotations, covering three task views:

  • Search-based Grounding
  • Search-based Segmentation
  • Search-based VQA
  • Benchmark Scale

  • 120 images
  • 473 annotated object instances
  • 645 unique QA pairs
  • 1927 task samples

Pixel-Searcher

The paper also proposes Pixel-Searcher, an agentic search-to-pixel workflow that resolves hidden target identities and binds them to boxes, masks, or grounded answers.

Results

Experiments show Pixel-Searcher achieves the strongest open-source performance across all three task views. Failure cases primarily stem from evidence acquisition, identity resolution, and visual instance binding.

---

*Auto-collected on 2026-05-14.*

Tags

#computer-vision#agentic-search#visual-grounding#benchmark#vqa#segmentation#deep-research#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619999