# Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations

arXiv: https://arxiv.org/abs/2506.17545 · HTML: https://mlsanity.com/paper/2506.17545/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 52 references that are in the map.
- First posted on arXiv 21 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [Uni3D: Exploring Unified 3D Representation at Scale](https://mlsanity.com/paper/2310.06773/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs](https://mlsanity.com/paper/2307.08581/) (2023)
- [Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models](https://mlsanity.com/paper/2410.03290/) (2024)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)

## Built on by (most cited first, 14 of 14)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2511.23075/) (2025)
- [AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models](https://mlsanity.com/paper/2511.10017/) (2025)
- [Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World](https://mlsanity.com/paper/2603.12746/) (2026)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning](https://mlsanity.com/paper/2508.12551/) (2025)
- [What if? Emulative Simulation with World Models for Situated Reasoning](https://mlsanity.com/paper/2603.06445/) (2026)
- [Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs](https://mlsanity.com/paper/2606.01215/) (2026)
- [3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding](https://mlsanity.com/paper/2603.04976/) (2026)
- [Token Warping Helps MLLMs Look from Nearby Viewpoints](https://mlsanity.com/paper/2604.02870/) (2026)
- [CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models](https://mlsanity.com/paper/2605.20165/) (2026)
- [SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning](https://mlsanity.com/paper/2608.07932/) (2026)
- [HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy](https://mlsanity.com/paper/2609.09941/) (2026)

## Abstract (arXiv)

Currently, utilizing large language models to understand the 3D world is becoming popular. Yet existing 3D-aware LLMs act as black boxes: they output bounding boxes or textual answers without revealing how those decisions are made, and they still rely on pre-trained 3D detectors to supply object proposals. We introduce Scene-R1, a video-grounded framework that learns to reason about 3D scenes without any point-wise 3D instance supervision by pairing reinforcement-learning-driven reasoning with a two-stage grounding pipeline. In the temporal grounding stage, we explicitly reason about the video and select the video snippets most relevant to an open-ended query. In the subsequent image grounding stage, we analyze the image and predict the 2D bounding box. After that, we track the object using SAM2 to produce pixel-accurate masks in RGB frames, and project them back into 3D, thereby eliminating the need for 3D detector-based proposals while capturing fine geometry and material cues. Scene-R1 can also adapt to the 3D visual question answering task to answer free-form questions directly from video. Our training pipeline only needs task-level 2D boxes or textual labels without dense 3D point-wise labels. Scene-R1 surpasses existing open-vocabulary baselines on multiple datasets, while delivering transparent, step-by-step rationales. These results show that reinforcement-learning-based reasoning combined with RGB-D video alone offers a practical, annotation-efficient route to trustworthy 3D scene understanding.