Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding
By: Yutao Tang , Cheng Zhao , Gaurav Mittal and more
Potential Business Impact:
Helps computers understand 3D worlds like we do.
Recent advances in 3D vision-language models (VLMs) highlight a strong potential for 3D scene understanding and reasoning. However, effectively tokenizing 3D scenes into holistic scene tokens, and leveraging these tokens across diverse 3D understanding tasks, remain highly challenging. We present NDTokenizer3D, a generalist 3D VLM that performs a wide range of 3D scene understanding tasks while naturally supporting human interactions, thereby bridging language-level reasoning with 3D spatial understanding. The core of our approach is a novel three-stage scene tokenization pipeline built upon a Multi-Scale Normal Distributions Transform (NDT) representation, paired with a Multi-Scale NDT Decoder (MSDec). Specifically, NDTokenizer3D first constructs a multi-scale NDT representation from raw high-resolution point clouds, preserving both global context and fine-grained geometric details. Next, the MSDec progressively fuses cross-scale NDT features, producing holistic scene tokens consumable by LLM endpoints. Beyond tokenization, MSDec is repurposed as a general interface for human-interactive prompting (points, boxes, masks) and segmentation-mask decoding, unifying diverse 3D scene understanding tasks within a single architecture. With this compact and unified design, NDTokenizer3D offers a fine-grained, general-purpose 3D VLM, achieving remarkable improvements in 3D Referring Segmentation, 3D Visual Question Answering, and 3D Dense Captioning.
Similar Papers
HMR3D: Hierarchical Multimodal Representation for 3D Scene Understanding with Large Vision-Language Model
CV and Pattern Recognition
Helps computers understand 3D spaces from pictures and words.
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
CV and Pattern Recognition
Helps robots explore and remember places better.
Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generation
CV and Pattern Recognition
Makes 3D pictures match words better.