# DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model

arXiv: https://arxiv.org/abs/2603.06090 · HTML: https://mlsanity.com/paper/2603.06090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [SpatialBot: Precise Spatial Understanding with Vision Language Models](https://mlsanity.com/paper/2406.13642/) (2024)
- [ImageBind-LLM: Multi-modality Instruction Tuning](https://mlsanity.com/paper/2309.03905/) (2023)
- [ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation](https://mlsanity.com/paper/1905.10089/) (2019)
- [Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks](https://mlsanity.com/paper/1605.02305/) (2016)
- [RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/1806.01054/) (2018)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have achieved impressive performance across various tasks such as image captioning and visual question answer(VQA); however, they often struggle to accurately interpret depth information inherent in visual data. In this work, we introduce DeepSight, the first dedicated depth MLLM designed to enhance three-dimensional scene understanding. Unlike conventional methods that align RGB image encodings with text, our approach takes advantage of the unique characteristics of depth images: single-channel grayscale images where the pixel values directly reflect depth cues to improve spatial reasoning. To address challenges associated with limited depth data and the inadequacy of simple channel replication, we construct a novel depth image-text pair dataset and a depth instruction dataset. Depth maps are generated from visual images using the GLPN model, and GPT-4 is employed to curate corresponding depth instructions, an approach validated by LLaVA. Additionally, we modify the ViT encoder in CLIP to incorporate local object information, thereby capturing the subtle continuous variations of depth more effectively. To evaluate the performance of our model, we develop a comprehensive depth question answer benchmark based on existing depth image datasets, which rigorously assesses understanding in typical depth map scenarios. Experimental results demonstrate that DeepSight significantly enhances depth perception and downstream task performance, marking a substantial step forward in multimodal three-dimensional understanding.