SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yang, Ma, Ming, Yu, Xiaomin, Ding, Pengxiang, Zhao, Han, Sun, Mingyang, Huang, Siteng, Wang, Donglin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917038149074944
author Liu, Yang
Ma, Ming
Yu, Xiaomin
Ding, Pengxiang
Zhao, Han
Sun, Mingyang
Huang, Siteng
Wang, Donglin
author_facet Liu, Yang
Ma, Ming
Yu, Xiaomin
Ding, Pengxiang
Zhao, Han
Sun, Mingyang
Huang, Siteng
Wang, Donglin
contents Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either require specialized sensors or fail to effectively exploit depth information for higher-order reasoning. To this end, we propose a novel Spatial Sense and Reasoning method, dubbed SSR, a novel framework that transforms raw depth data into structured, interpretable textual rationales. These textual rationales serve as meaningful intermediate representations to significantly enhance spatial reasoning capabilities. Additionally, we leverage knowledge distillation to compress the generated rationales into compact latent embeddings, which facilitate resource-efficient and plug-and-play integration into existing VLMs without retraining. To enable comprehensive evaluation, we introduce a new dataset named SSR-CoT, a million-scale visual-language reasoning dataset enriched with intermediate spatial reasoning annotations, and present SSRBench, a comprehensive multi-task benchmark. Extensive experiments on multiple benchmarks demonstrate SSR substantially improves depth utilization and enhances spatial reasoning, thereby advancing VLMs toward more human-like multi-modal understanding. Project page: https://yliu-cs.github.io/SSR.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
Liu, Yang
Ma, Ming
Yu, Xiaomin
Ding, Pengxiang
Zhao, Han
Sun, Mingyang
Huang, Siteng
Wang, Donglin
Computer Vision and Pattern Recognition
Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either require specialized sensors or fail to effectively exploit depth information for higher-order reasoning. To this end, we propose a novel Spatial Sense and Reasoning method, dubbed SSR, a novel framework that transforms raw depth data into structured, interpretable textual rationales. These textual rationales serve as meaningful intermediate representations to significantly enhance spatial reasoning capabilities. Additionally, we leverage knowledge distillation to compress the generated rationales into compact latent embeddings, which facilitate resource-efficient and plug-and-play integration into existing VLMs without retraining. To enable comprehensive evaluation, we introduce a new dataset named SSR-CoT, a million-scale visual-language reasoning dataset enriched with intermediate spatial reasoning annotations, and present SSRBench, a comprehensive multi-task benchmark. Extensive experiments on multiple benchmarks demonstrate SSR substantially improves depth utilization and enhances spatial reasoning, thereby advancing VLMs toward more human-like multi-modal understanding. Project page: https://yliu-cs.github.io/SSR.
title SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.12448