SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision and language tasks. However, their ability to reason about spatial arrangements remains limited. In this work, we introduce Spatial Region GPT (SpatialRGPT) to enhance VLMs' spatial perception and reasoning capabilities. SpatialRGPT advances VLMs' spatial understanding through two key innovations: (1) a data curation pipeline that enables effective learning of regional representation from 3D scene graphs, and (2) a flexible plugin module for integrating depth information into the visual encoder of existing VLMs. During inference, when provided with user-specified region proposals, SpatialRGPT can accurately perceive their relative directions and distances. Additionally, we propose SpatialRGBT-Bench, a benchmark with ground-truth 3D annotations encompassing indoor, outdoor, and simulated environments, for evaluating 3D spatial cognition in VLMs. Our results demonstrate that SpatialRGPT significantly enhances performance in spatial reasoning tasks, both with and without local region prompts. The model also exhibits strong generalization capabilities, effectively reasoning about complex spatial relations and functioning as a region-aware dense reward annotator for robotic tasks. Code, dataset, and benchmark are released at https://www.anjiecheng.me/SpatialRGPT

Paper

Similar papers

Peer review

Reviewer v4dm7/10 · confidence 4/52024-07-11

Summary

This paper introduces SpatialRGPT, targeting at enhancing the spatial reasoning abilities of VLMs. The authors introduce a data curation pipeline along with a benchmark that facilitates the learning and evaluation of 3D spatial knowledge. Experiments show that SpatialRGPT thrives at spatial reasoning and performs comparable to SOTA on standard VQA benchmarks. The authors also showcase some real-world applications of such a model by using it for complex spatial reasoning and as a reward annotator for robot manipulation.

Strengths

1. The paper introduces a data curation pipeline that facilitates spatial relation learning, along with a benchmark that's designed specifically for this important task, which will all be made available, making it easy to follow. 2. This paper introduces a plug-and-play module that process depth information for VLM. Experimental results showcase that the module is useful for cases that involves reasoning among behind/front, wide/thin, and estimating distances. 3. Results on real robot shows that the learned spatial relation representation can indeed be used for downstream tasks.

Weaknesses

1. When constructing 3D scene graph, the author mentioned using 3D axis-aligned bounding boxes for objects to compute the width and height. This could lead to inaccurate measure of the object size. It'd be great if the author could show some results on how much does this affect the overall data quality, i.e. how many objects are measured inaccurately because of the AABB assumptions of the bounding boxes. 2. When discussing the potential real-world application, the author showcased SpatialRGPT can be used as a dense reward annotator. However, the annotation process still needs manually defining regions of interest for every frame in the demonstration video, hindering its use at a broader impact. 3. The width and height result in Table 1 suggests that SpatialRGPT underperforms the best model, i.e. GPT-4V by 10.5 in success rate, this is a major concern to me since GPT-4V only has commonsense knowledge on the object size and still outperforms SpatialRGPT, which is trained on object size knowledge, by a large margin. Therefore, I'm wondering if the data of object size is useful, i.e. without this portion of data, how would SpatialRGPT perform in the task of reasoning about width and height.

Questions

1. Since Open Spatial Dataset plays an important role in enhancing the ability of spatial reasoning, I'm wondering if the data that targets at different aspect would affect each other, i.e. if I remove the QA pair regarding width and height, will it affect the models performance on answering big/small questions? 2. Despite the task is targeted at region-based spatial reasoning, I'm wondering how well the model would perform on VQA tasks that includes single region but multi-hop reasoning, i.e. what is the object on the table to the right of <region1>?

Rating

7

Confidence

4

Soundness

3

Presentation

4

Contribution

3

Limitations

The authors have adequately addressed the limitations and potential negative societal impact of their work.

Reviewer hHf26/10 · confidence 4/52024-07-12

Summary

This paper constructs region-aware spatial reasoning QA datasets from existing sources, resulting in the Open Spatial Dataset (OSD). Based on the OSD, they develop a model called SpatialRGPT, which integrates depth information to enable effective representation of regional information and acquisition of spatial knowledge. Experimental results demonstrate the superior spatial reasoning ability of the proposed model and its potential applications in robotics.

Strengths

1. The proposed dataset OSD is well-crafted with open-vocabulary regions, which should benefit future research by enhancing models’ spatial reasoning abilities. 2. Integrating depth information into the VLM is a novel approach for achieving more accurate spatial reasoning. 3. The paper is well-written and easy to follow.

Weaknesses

1. The SpatialRGPT-Bench is constructed through the proposed data generation pipeline, sharing the same answer formats as the OSD dataset on which the SpatialRGPT is trained. This may introduce bias when directly comparing it with other models not trained on the OSD dataset. 2. There is a lack of clarity regarding the size of SpatialRGPT used in the experiments. In Table 1, it is compared with a 34B model (LLaVA v1.6), while in Table 2, it is compared with 7B models.

Questions

1. In Figure 4, the fifth QA example asks, "What kind of vehicles would not fit in?". Is this an example from the SpatialRGPT-Bench, and which category does it belong to? This question involves height, width, and depth of the garage area, which may not align well with the current categories and metrics used for evaluation.

Rating

6

Confidence

4

Soundness

3

Presentation

3

Contribution

3

Limitations

See Weaknesses.

Reviewer ojLE7/10 · confidence 4/52024-07-13

Summary

The paper introduces a novel approach for generating 3D, region-aware annotations from 2D images, transforming scene graphs into spatial QA training data for VLMs using a combination of template-based and LLM approaches. Key contributions include: 1. A novel pipeline for automatic generation of complex, metric spatial QA data. 2. A proposed depth adapter to include relative depth maps as input to the VLM. 3. Benchmarking the generated annotations against state-of-the-art methods, showing improvements in spatial reasoning tasks.

Strengths

- The integration of scene graphs with template-based and LLM-based QA generation, along with the use of a depth map adapter, provides a novel approach to spatial QA VLM training. - The experimental results are strong, demonstrating significant improvements over state-of-the-art models like GPT-4V+SoM and Llava-Next. - The methodology is well-explained, with clear descriptions of the data collection process and the architecture of the proposed model.

Weaknesses

- The paper lacks a detailed analysis of how closely the questions in the evaluation set match the templated questions from the data generation pipeline. It is unclear if the formatting provides an unfair advantage to the model, and whether altering the evaluation question formatting affects model performance. - The paper does not include a discussion on whether the depth adapter alone, when trained on non-spatial data, improves performance. Additionally, it is unclear why SpatialVLM, a relevant baseline, was not included in the comparisons.

Questions

1. How close are the questions in the evaluation set to the templated questions in the data generation pipeline? What steps are taken to ensure that the question and answer formatting do not give an evaluation advantage? If you change the evaluation question formatting, does it affect the model's performance? 2. Does the depth adapter addition alone, trained on non-spatial data, provide a performance boost even without the added spatial training data? 3. Why is SpatialVLM not included as a baseline, given its relevance? 3. What is the human performance on the evaluation set or a subset, given that humans may be worse than the model at metric spatial reasoning?

Rating

7

Confidence

4

Soundness

4

Presentation

3

Contribution

4

Limitations

The authors discuss limitations in the appendix. Moving limitation discussion to the main paper and addressing the questions outlined above would strengthen the paper.

Reviewer y3Gs6/10 · confidence 5/52024-07-18

Summary

The paper introduces SpatialRGPT, a framework designed to enhance region-level spatial reasoning in Visual Language Models (VLMs) by incorporating 3D and region-aware visual encoder architecture. The authors present a scalable data pipeline to generate region-aware spatial reasoning questions and answers from existing datasets, resulting in the creation of the Open Spatial Dataset (OSD). To evaluate the model's performance, they introduce SpatialRGPT-Bench, a comprehensive benchmark with ground-truth 3D annotations. The paper demonstrates practical applications of SpatialRGPT, such as serving as a region-aware dense reward annotator for robotics and a stand-alone complex spatial reasoner.

Strengths

- The paper addresses the important problem of enhancing the spatial perception capabilities of multimodal LLMs. - It creates a large-scale training dataset with millions of examples. - The paper is well-organized and easy to follow, clearly explaining the authors' motivations at each step. - The effectiveness of the approach is demonstrated not only in vision-language tasks but also in embodied tasks.

Weaknesses

- The biggest weakness, in my opinion, is the evaluation. The evaluation using SpatialRGPT-Bench shares the same data creation pipeline as the training data. This means the good performance on SpatialRGPT-Bench might just reflect the model learning the language style of the training data. Using GPT-4 for evaluation further biases the assessment towards responses that include numerical language, as seen in the teaser example: “The height of..1....is 204.54 feet. Assuming each floor is about 10 feet high, the total number of floors would be 20.454. Since you can’t have a fraction of a floor, the total number of floors would be approximately 20.” This type of response, while technically correct, doesn’t align with normal logical thinking. Therefore, a proper evaluation should be conducted on benchmarks like BLINK, especially those related to 3D tasks like depth. - In Table 2, SpatialRGPT-Depth underperforms the original VILA in 6 out of 8 benchmarks. - What if we use an off-the-shelf pretrained 3D detector on SpatialRGPT-Bench and then use an LLM to answer questions based on the cuboids from the 3D detector? On other benchmarks like BLINK, is SpatialRGPT better, or is the data curation method of first extracting 3D scene graphs and then using an LLM to summarize better? - Does stage three of training (Visual Instruction-tuning) require updating all model parameters? - Does the training data need to overlay all region proposals on the original images, like in Fig. 2, similar to Set-of-Marks? - The model explanation is unclear, and Figure 3 is confusing. So, the input includes RGB, depth maps, and region proposals (masks or bounding boxes)? Then, a shared visual encoder extracts global features from the RGB image and depth map, and independent connectors project the global RGB/depth feature embeddings into the word embedding space? How many tokens represent RGB and depth, respectively? For region-level features, is each object represented by two tokens, one from the RGB feature and one from the depth feature? Does the Region Feature Extractor take features from the last layer of the visual encoder? Do the RGB and depth features share the same Region Feature Extractor? Figure 3 shows it as shared, but the appendix suggests they are independent. - Why does the model need to extract region-level tokens separately? Couldn’t the region proposal information be included in the image-level token sequence through visual prompting, like in Set-of-Marks (SOM)? If LLAVA+SOM were trained on OSD, it might also work. - The model size is not reported—Is it 7B? - Typos: Line 327 should refer to Fig. 5.

Questions

Please answer the questions in weakness section.

Rating

6

Confidence

5

Soundness

2

Presentation

3

Contribution

3

Limitations

Please refer to the weakness section.

Reviewer hHf22024-08-10

Thank you for your response, which has addressed my concern about the fairness in evaluation. I would like to raise the rating from 5 to 6.

Reviewer ojLE2024-08-10

Thank you for your comments

Thank you to the authors for their comments and the additional experiments. My concerns have been addressed. The new experiments on rephrased questions and BLINK are valuable additions to the work. I have updated my score to a 7.

Reviewer y3Gs2024-08-11

Thanks for the rebuttal

The additional evaluations provided by the author have addressed most of my concerns, and the author has also clarified the unclear parts of the paper. I hope the author can incorporate these details into the updated version to make the paper even better. I will raise my score to 6.

Reviewer v4dm2024-08-12

Thank you for your response

Thank you for your responses. They have adequately addressed my concerns regarding the data quality and its effects on the model itself. I hope the author can put the additional results in the revised version. Considering the value of this work, I will keep my original score.

Program Chairsdecision2024-09-25

Decision

Accept (poster)

© 2026 NYSGPT2525 LLC