Paper Detail

PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding

Shaohui Dai, Yansong Qu, You Shen, Shengchuan Zhang, Liujuan Cao

arxiv Score 11.3

Published 2026-06-04 · First seen 2026-06-05

General AI

Abstract

Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, reason about, and ground both objects and their parts in 3D scenes. To enable training and evaluation of part-aware 3D scene understanding, we introduce ScenePart, a synthetic 3D scene dataset with part-level annotations and language instructions. We further develop Part-Aware 3D Representation Learning to enrich 3D visual representations with fine-grained part-level semantics, and propose Hierarchical Segmentation Query Generation to ground part targets via hierarchical object-part queries. Extensive experiments show that our method substantially improves part-level question answering and referring segmentation, while also achieving strong performance across object-level vision-language tasks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{dai2026par3d,
  title = {PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding},
  author = {Shaohui Dai and Yansong Qu and You Shen and Shengchuan Zhang and Liujuan Cao},
  year = {2026},
  abstract = {Recent advances in 3D multimodal large language models (3D-MLLMs) have enabled unified solutions for 3D scene understanding tasks, including visual question answering, captioning, and referring segmentation. However, existing 3D-MLLMs remain largely object-centric, limiting their ability to model fine-grained part structures that are essential for embodied interaction with 3D environments. In this work, we present PAR3D, a unified part-aware 3D-MLLM framework that enables models to understand, r},
  url = {https://arxiv.org/abs/2606.06485},
  keywords = {cs.CV},
  eprint = {2606.06485},
  archiveprefix = {arXiv},
}

Metadata

{}