RegionReasoner: Region-Grounded Multi-Round Visual Reasoning

• URL: http://arxiv.org/abs/2602.03733v1
• Date: Tue, 03 Feb 2026 16:52:16 GMT
• Title: RegionReasoner: Region-Grounded Multi-Round Visual Reasoning
• Authors: Wenfang Sun, Hao Chen, Yingjun Du, Yefeng Zheng, Cees G. M. Snoek,
• Abstract summary: RegionReasoner is a reinforcement learning framework for visual reasoning.<n>It enforces grounded reasoning by requiring each reasoning trace to explicitly cite the corresponding reference bounding boxes.<n>RegionReasoner is optimized with structured rewards combining grounding fidelity and global-local semantic alignment.
• Score: 69.75509909581133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual contexts. To address this limitation, we introduce a new multi-round visual reasoning benchmark with training and test sets spanning both detection and segmentation tasks, enabling systematic evaluation under iterative reasoning scenarios. We further propose RegionReasoner, a reinforcement learning framework that enforces grounded reasoning by requiring each reasoning trace to explicitly cite the corresponding reference bounding boxes, while maintaining semantic coherence via a global-local consistency reward. This reward extracts key objects and nouns from both global scene captions and region-level captions, aligning them with the reasoning trace to ensure consistency across reasoning steps. RegionReasoner is optimized with structured rewards combining grounding fidelity and global-local semantic alignment. Experiments on detection and segmentation tasks show that RegionReasoner-7B, together with our newly introduced benchmark RegionDial-Bench, considerably improves multi-round reasoning accuracy, spatial grounding precision, and global-local consistency, establishing a strong baseline for this emerging research direction.

Related papers

• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach [41.001581773172695]
  We present Geo-R, a retrieval-free framework that uncovers structured reasoning paths from existing ground-truth coordinates.<n>We propose the Chain of Region, a rule-based hierarchical reasoning paradigm that generates precise, interpretable supervision.<n>Our approach bridges structured geographic reasoning with direct spatial supervision, yielding improved localization accuracy, stronger generalization, and more transparent inference.
  arXiv  Detail & Related papers  (2026-01-01T16:51:41Z)
• Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning [63.109585527799005]
  GroundingAgent is a visual grounding framework that operates without task-specific fine-tuning.<n>It achieves an average zero-shot grounding accuracy of 65.1 % on widely-used benchmarks.<n>It also offers strong interpretability, transparently illustrating each reasoning step.
  arXiv  Detail & Related papers  (2025-11-24T03:11:08Z)
• REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language [0.1388281922732496]
  We frame this problem of forgery detection as a prompt-driven visual reasoning task, leveraging the semantic alignment capabilities of large vision-language models.<n>We propose two approaches - (1) Holistic Scene-level Evaluation that relies on the physics, semantics, perspective, and realism of the image as a whole and (2) Region-wise anomaly detection that splits the image into multiple regions and analyzes each of them.
  arXiv  Detail & Related papers  (2025-08-18T00:42:02Z)
• DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models [9.109484087832058]
  DiffRIS is a novel framework that harnesses the semantic understanding capabilities of pre-trained text-to-image diffusion models for RRSIS tasks.<n>Our framework introduces two key innovations: a context perception adapter (CP-adapter) and a cross-modal reasoning decoder (PCMRD)
  arXiv  Detail & Related papers  (2025-06-23T02:38:56Z)
• GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains [20.788130896943663]
  Geo Reason Enhancement (GRE) Suite is a novel framework that augments Visual Language Models with structured reasoning chains for interpretable location inference.<n>First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis.<n>Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision.
  arXiv  Detail & Related papers  (2025-05-24T13:48:57Z)
• VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought [51.43082554363725]
  We introduce textbfVLM-R$3$ (textbfVisual textbfLanguage textbfModel with textbfRegion textbfRecognition and textbfReasoning), a framework that equips an MLLM with the ability to decide emph when additional visual evidence is needed.<n>Experiments on MathVista, ScienceQA, and other benchmarks show that VLM-R$3$ sets a new
  arXiv  Detail & Related papers  (2025-05-22T03:50:13Z)
• Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning [50.88504784466931]
  Multi-task dense prediction involves semantic segmentation, depth estimation, and surface normal estimation. Existing solutions typically rely on learning global image representations for global cross-task image matching. Our proposal involves modeling region-wise representations using Gaussian Distributions.
  arXiv  Detail & Related papers  (2024-03-15T12:41:30Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• FindIt: Generalized Localization with Natural Language Queries [43.07139534653485]
  FindIt is a simple and versatile framework that unifies a variety of visual grounding and localization tasks. Key to our architecture is an efficient multi-scale fusion module that unifies the disparate localization requirements. Our end-to-end trainable framework responds flexibly and accurately to a wide range of referring expression, localization or detection queries.
  arXiv  Detail & Related papers  (2022-03-31T17:59:30Z)
• Point-Level Region Contrast for Object Detection Pre-Training [147.47349344401806]
  We present point-level region contrast, a self-supervised pre-training approach for the task of object detection. Our approach performs contrastive learning by directly sampling individual point pairs from different regions. Compared to an aggregated representation per region, our approach is more robust to the change in input region quality.
  arXiv  Detail & Related papers  (2022-02-09T18:56:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.