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: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...
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: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: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...
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.
The paper investigates how much semantic information is lost when frozen foundation models are combined for few‑shot 3D segmentation. By varying the number of retained semantic alternatives before fusion, the authors show that keeping the full distribution of class scores yields higher harmonic‑mean IoU than collapsing to a single class. Experiments on ScanNet200 and ScanNet++ confirm that full‑distribution fusion consistently outperforms top‑1 and other operators, and that most useful information is recovered by retaining a compact set of plausible alternatives.
LangMap introduces a human‑verified benchmark for language‑conditioned goal navigation (LGN) that spans four hierarchical semantic levels—scene, room, region, and instance—within real‑world indoor 3D scans. The dataset, built on HM3D, contains 18K tasks with concise and detailed descriptions for 414 object categories, and its contrastive annotation protocol ensures high‑quality, discriminative region and instance labels. Evaluation shows that LangMap’s descriptions improve text‑to‑view matching accuracy by 23 points over GOAT‑Bench and achieve a 92.5% unique‑and‑correct match rate in an independent human audit, while a proposed RGB‑only baseline, PlaNaVid, attains top‑tier success rates without depth or 3D scene representations.
SpatialMem is a memory-based system that fuses 3D geometry, semantics, and language into a single queryable representation. Starting from casually recorded egocentric RGB video, it reconstructs metrically scaled interior scenes, identifies structural 3D anchors (walls, doors, windows), and links open‑vocabulary object nodes to evidence patches, visual embeddings, and two‑layer descriptions at 3D coordinates, enabling spatial‑relation reasoning, language‑directed retrieval, and QA without special sensors. The system is evaluated at scale on public benchmarks, achieving competitive scores on VSI‑Bench, OpenEQA, and ScanNet, while maintaining a compact index of about 14 KB per scene.
GeoGR introduces a two‑stage framework for efficient 3D vision‑language models. The first stage, GeoSemZip, compresses multi‑view visual tokens into compact 3D voxel representations while preserving important scene information through contextual anchors. The second stage, GroupRoute, dynamically routes tokens through the language model, allowing low‑relevance tokens to skip layers and rejoin later, thereby reducing computation without significant loss of performance.
arXiv:2606. 31148v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions.
STRUCTPARTS is a new framework that reuses holistic 3D priors to generate part‑decomposed 3D assets. It introduces a dual‑frame coordinate interleaving mechanism, interpreting each shape latent under both part‑local and object‑global reference frames and processing them with a global‑local inter‑leaved transformer. Using a segmented mesh scaffold as structural input, the method achieves detailed intra‑part geometry and coherent inter‑part structure with lightweight finetuning, outperforming prior part‑decomposed models on PartObjaverse‑Tiny while enabling part‑mesh refinement and editing.