# Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

arXiv: https://arxiv.org/abs/2504.01901 · HTML: https://mlsanity.com/paper/2504.01901/

## Key facts

- Cited by 63 papers in the map (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 72 of its 98 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## 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, 30 of 72)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://mlsanity.com/paper/2203.06604/) (2022)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)

## Built on by (most cited first, 30 of 63)

- [VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction](https://mlsanity.com/paper/2505.20279/) (2025)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors](https://mlsanity.com/paper/2505.24625/) (2025)
- [Scaling Spatial Intelligence with Multimodal Foundation Models](https://mlsanity.com/paper/2511.13719/) (2025)
- [VGR: Visual Grounded Reasoning](https://mlsanity.com/paper/2506.11991/) (2025)
- [Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology](https://mlsanity.com/paper/2507.07999/) (2025)
- [Reconstruction Alignment Improves Unified Multimodal Models](https://mlsanity.com/paper/2509.07295/) (2025)
- [Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence](https://mlsanity.com/paper/2510.20579/) (2025)
- [Visual Representation Alignment for Multimodal Large Language Models](https://mlsanity.com/paper/2509.07979/) (2025)
- [Holistic Evaluation of Multimodal LLMs on Spatial Intelligence](https://mlsanity.com/paper/2508.13142/) (2025)
- [N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2512.16561/) (2025)
- [Reasoning in Space via Grounding in the World](https://mlsanity.com/paper/2510.13800/) (2025)
- [Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs](https://mlsanity.com/paper/2510.18876/) (2025)
- [Thinking with Geometry: Active Geometry Integration for Spatial Reasoning](https://mlsanity.com/paper/2602.06037/) (2026)
- [Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images](https://mlsanity.com/paper/2511.07222/) (2025)
- [SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding](https://mlsanity.com/paper/2506.21924/) (2025)
- [CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling](https://mlsanity.com/paper/2602.13191/) (2026)
- [MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs](https://mlsanity.com/paper/2511.07250/) (2025)
- [Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps](https://mlsanity.com/paper/2601.11442/) (2026)
- [MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues](https://mlsanity.com/paper/2510.17722/) (2025)
- [Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning](https://mlsanity.com/paper/2603.01385/) (2026)
- [Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding](https://mlsanity.com/paper/2603.19235/) (2026)
- [Video Spatial Reasoning with Object-Centric 3D Rollout](https://mlsanity.com/paper/2511.13190/) (2025)
- [Vision-Language Memory for Spatial Reasoning](https://mlsanity.com/paper/2511.20644/) (2025)
- [S2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance](https://mlsanity.com/paper/2512.01223/) (2025)
- [Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models](https://mlsanity.com/paper/2603.01400/) (2026)
- [Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators](https://mlsanity.com/paper/2606.06476/) (2026)
- [Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts](https://mlsanity.com/paper/2505.21079/) (2025)
- [POMA-3D: The Point Map Way to 3D Scene Understanding](https://mlsanity.com/paper/2511.16567/) (2025)
- [Unlocking Dense Metric Depth Estimation in VLMs](https://mlsanity.com/paper/2605.15876/) (2026)

## Abstract (arXiv)

The rapid development of Large Multimodal Models (LMMs) for 2D images and videos has spurred efforts to adapt these models for interpreting 3D scenes. However, the absence of large-scale 3D vision-language datasets has posed a significant obstacle. To address this issue, typical approaches focus on injecting 3D awareness into 2D LMMs by designing 3D input-level scene representations. This work provides a new perspective. We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure. Specifically, it incorporates cross-view and global-view reconstruction. The former requires reconstructing masked views by aggregating overlapping information from other views. The latter aims to aggregate information from all available views to recover Bird's-Eye-View images, contributing to a comprehensive overview of the entire scene. Empirically, Ross3D achieves state-of-the-art performance across various 3D scene understanding benchmarks. More importantly, our semi-supervised experiments demonstrate significant potential in leveraging large amounts of unlabeled 3D vision-only data.