Pith. sign in

REVIEW 19 cited by

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.23478 v1 pith:ERF45AGU submitted 2025-07-31 cs.CV

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

classification cs.CV
keywords d-r1reasoningsceneunderstandingrewardvlmscapabilitiesdata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning and generalization due to limitations in high-quality spatial data and the static nature of viewpoint assumptions. To address these challenges, we propose 3D-R1, a foundation model that enhances the reasoning capabilities of 3D VLMs. Specifically, we first construct a high-quality synthetic dataset with CoT, named Scene-30K, leveraging existing 3D-VL datasets and a data engine based on Gemini 2.5 Pro. It serves as cold-start initialization data for 3D-R1. Moreover, we leverage RLHF policy such as GRPO in the reinforcement learning training process to enhance reasoning capabilities and introduce three reward functions: a perception reward, a semantic similarity reward and a format reward to maintain detection accuracy and answer semantic precision. Furthermore, we introduce a dynamic view selection strategy that adaptively chooses the most informative perspectives for 3D scene understanding. Extensive experiments demonstrate that 3D-R1 delivers an average improvement of 10% across various 3D scene benchmarks, highlighting its effectiveness in enhancing reasoning and generalization in 3D scene understanding. Code: https://github.com/AIGeeksGroup/3D-R1. Website: https://aigeeksgroup.github.io/3D-R1.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.

  2. LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue

    cs.CV 2026-05 unverdicted novelty 7.0

    LMM-Track4D formulates a trajectory-grounded dialogue task, releases Track4D-Bench with 526 samples, and proposes RTGE encoding, TRK state token, and OSK-RA decoder to elicit better 4D spatiotemporal reasoning in LMMs.

  3. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 unverdicted novelty 7.0

    A new coupled boundary integral method models steadily moving semi-infinite fractures in plane poroelasticity, solving for mechanical deformation and fluid exchange with verification on analytical test cases.

  4. Token Warping Helps MLLMs Look from Nearby Viewpoints

    cs.CV 2026-04 unverdicted novelty 7.0

    Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.

  5. Holo-Captioning: Toward the Text Equivalent of 3D Scenes

    cs.CV 2026-07 conditional novelty 6.5

    HoloScribe generates pure-text structured captions of all entities, boxes, attributes and relations in 3D indoor scenes and outperforms dense captioners and 3D LLMs on a new 15K-scene benchmark.

  6. VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations

    cs.CV 2026-03 conditional novelty 6.5

    Sparse multi-view reasoning is largely unsolved for VLMs; grounded CoT with visual evidence improves moderate cases and transfers to real data, but deep multi-hop reasoning still scales poorly.

  7. Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering

    cs.CV 2026-07 conditional novelty 6.0

    Online geometry-aware voxel overlap pruning removes up to 50% of visual tokens from multi-view 3D scenes while improving zero-shot 3D QA on Qwen VL models.

  8. Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views

    cs.CV 2026-06 unverdicted novelty 6.0

    DR-MV3D decomposes MV3D-VQA into global map construction, question-conditioned view planning, and egocentric grounding, supervised by global consistency and local trajectory rewards optimized via GRPO.

  9. DriveJudge: Rethinking Autonomous Driving Evaluation with Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    DriveJudge combines VLM reasoning with rule functions on a new 33,577-sample human-annotated dataset, outperforming EPDMS by 21.23 AUC on quality classification and DriveCritic by 6.5% on trajectory preference.

  10. Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs

    cs.CV 2026-05 unverdicted novelty 6.0

    APEIRIA transfers symbolic reasoning traces into natural-language chain-of-thought inside 3D MLLMs, matching SOTA 3D MLLM performance while retaining modular interpretability on grounding, QA, and captioning benchmarks.

  11. Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs

    cs.CV 2026-05 unverdicted novelty 6.0

    APEIRIA distills neuro-symbolic 3D reasoning programs into 3D MLLMs through a curriculum that transfers stepwise verification patterns to achieve transparent yet flexible spatial reasoning.

  12. Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation

    cs.CV 2026-04 unverdicted novelty 6.0

    Layer analysis of DINOv3 shows non-uniform 3D geometric knowledge concentrated in deeper layers, enabling a last-layer-centric recombination module that improves monocular depth estimation accuracy to state-of-the-art levels.

  13. GeoWorld: Geometric World Models

    cs.CV 2026-02 unverdicted novelty 6.0

    GeoWorld applies hyperbolic geometry to JEPA world models and introduces geometric reinforcement learning, reporting modest success-rate gains of ~3% and ~2% on 3- and 4-step planning tasks versus V-JEPA 2.

  14. Grounded 3D-Aware Spatial Vision-Language Modeling

    cs.CV 2026-05 unverdicted novelty 5.0

    GR3D is a VLM that combines explicit 2D, implicit 2D, and monocular 3D grounding mechanisms to improve performance on spatial understanding benchmarks.

  15. Steadily moving semi-infinite fracture in plane poroelasticity

    physics.geo-ph 2026-04 conditional novelty 5.0

    XEmbodied achieves SOTA on 18 embodied VQA benchmarks by fusing 3D geometric tokens and distilled physical cues into a 30B VLM with progressive curriculum training.

  16. UniMesh: Unifying 3D Mesh Understanding and Generation

    cs.CV 2026-04 unverdicted novelty 5.0

    UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.

  17. VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

    cs.CV 2026-07 conditional novelty 4.0

    VaseMuseum is a training-free multimodal agent that combines DeepResearch-style retrieval, source/response reliability control, and best-of-K reranking to improve citation validity and reduce hallucination for museum ...

  18. XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments

    cs.CV 2026-04 unverdicted novelty 4.0

    XEmbodied is a foundation model that integrates 3D geometric and physical signals into VLMs using a 3D Adapter and Efficient Image-Embodied Adapter, plus progressive curriculum and RL post-training, to improve spatial...

  19. A Survey of Reinforcement Learning for Large Reasoning Models

    cs.CL 2025-09 accept novelty 3.0

    A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.