arXiv Computer Vision
3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 28
GraphWrit3R: End-to-End 3D Scene Graph Writing
arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functio...
arXiv Computer Vision
Oct 5
Octrees as an Explicit 3D Language
arXiv:2610.02388v1 Announce Type: new Abstract: Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes...
arXiv AI
Oct 26
Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition
The paper introduces PFIR, a Part-level Functional Inference for Recognition framework that reverses the typical function-as-annotation flow in 3D multimodal large language models (MLLMs). By leveraging PartNeXt segmentation and a curriculum of 507K QA pairs with functional chains of thought, PFIR trains a dual-objective reinforcement learning model (GRPO) to perform strict functional reasoning and descriptive grounding. In zero‑shot tests, PFIR improves accuracy from 60.5% to 66.7%, especially on geometrically ambiguous samples, demonstrating that part‑level functional reasoning enhances generalizable 3D recognition.
arXiv Computer Vision
Oct 22
LLMSeg: Training-Free Text-Prompted Image Segmentation with B-Splines
arXiv:2610.29409v1 Announce Type: new Abstract: Promptable segmentation models such as SAM 3 achieve remarkable open-vocabulary performance but require dedicated architectures, large-scale annotation...
arXiv Computer Vision
Oct 21
P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
arXiv:2610.28018v1 Announce Type: new Abstract: Examining existing benchmarks for grounding in 3D VLMs reveals a pervasive "semantic leakage" in the evaluation and prompting protocols: a heavy relian...
arXiv Computer Vision
Oct 16
Training-Free Target-Aware Refinement of 3D Gaussian Language Map
The paper introduces a training‑free, target‑aware refinement method for 3D Gaussian language maps distilled from vision‑language features. By blending the visual embedding within user‑specified target regions with the corresponding text embedding using a convex combination, the method improves target localization while preserving open‑vocabulary queryability. The authors derive the optimal blending coefficient analytically, avoid hyperparameters, and demonstrate consistent gains across three benchmarks, including a real‑world robot navigation demo.