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
- 120 images
- 473 annotated object instances
- 645 unique QA pairs
- 1927 task samples
Benchmark Scale
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.*