Exploiting Vision Language Model for Training-Free 3D Point Cloud Understanding via Improved Graph Score Propagation.

TextFM: Robust Semi-dense Feature Matching with Language Guidance

LiDAR Point Cloud Oversegmentation via SAM-based Knowledge Distillation

A SAM-guided framework for point cloud oversegmentation that significantly improves boundary recall and maintains high oracle accuracy while maintaining high oracle accuracy, and generalizes well to unseen datasets without retraining, showing strong cross-dataset inference capability.

On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models

3D point cloud-language models (3D-LLMs) enable 3D understanding by pairing point cloud encoders with large language models, but existing methods rely on costly multi-modal encoders (e.g., ULIP-2) that require image-text-point cloud alignment on 8x A100-scale compute, creating high barriers for research and deployment. In this work, we systematically investigate whether low-cost self-supervised point cloud encoders, specifically PCP-MAE and Point-MAE, can serve as effective alternatives. Using MiniGPT-3D as our testbed, we evaluate 7 encoder initialization/pre-training setups (1 multi-modal baseline, 5 self-supervised, 1 random init) under frozen and unfrozen fine-tuning (12 total groups), across 2 architectures (MaskTransformer, PointTransformer), 3 objectives (PCP-MAE, Point-MAE, random init), and 2 datasets (Objaverse 660K, ShapeNet55-34 approximately 50K). Our experiments reveal three key findings: (1) The four-stage MiniGPT-3D pipeline can effectively train a 3D encoder from random initialization: an end-to-end trained random init encoder reaches 52.50% open-vocabulary accuracy and 44.45 captioning score, approaching top pre-trained variants; (2) Architecture and pre-training objective show strong crossover interaction: PCP-MAE + MaskTransformer achieves 59.00% accuracy (best self-supervised), while Point-MAE + MaskTransformer drops to 46.50%, with the pattern reversed for PointTransformer; (3) Closed-set ModelNet40 classification remains a core weakness of purely geometric encoders, reaching only ~13-18% accuracy vs. ~62% for the multi-modal baseline, even after end-to-end fine-tuning. Our results offer practical guidelines for cost-effective 3D-LLM design and reveal interaction patterns between self-supervised objectives and encoder architectures.

Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmark

Generalized few-shot 3D point-cloud segmentation (GFS-PCS) asks a model to segment a scene into many base classes seen at training time and a set of novel classes. The state of the art reaches novel classes by reconciling a dense but noisy 3D vision-language prior with the few-shot support, but it pays for this with base 3D labels, per-episode training, and the support annotations themselves. We ask how far the same reconciliation can go with none of these: no training, no 3D labels, and not even the few-shot support. We pair a frozen 3D vision-language model (RegionPLC) as a dense prior with a frozen promptable concept segmenter (SAM3), prompted by the bare novel class names and lifted from posed RGB views, and reconcile the two by cross-view consistency: a point becomes novel only when enough of the views that see it agree. On the ScanNet200 GFS-PCS benchmark this fully training-free, open-vocabulary pipeline improves novel mIoU by +2.6 over the training-free dense prior while holding base accuracy within 0.5, and recovers a third (33%) of the novel-class gap to the trained state of the art that uses far more supervision. We further show that injecting the few-shot support into the pipeline, as a fusion gate and as a prototypical dense classifier, adds nothing over consistency alone and in fact degrades it through the classifier, which is why the method needs no support at all. On the harder ScanNet++ benchmark, where the dense prior is far weaker on novel classes, the same pipeline nearly doubles novel mIoU (+15.7, from 16.2 to 31.9) at a 1.7 base cost, lifting the harmonic mean from 21.5 to 31.1

Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding

Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation tasks. We argue that a key limitation is geometry-aware decoding: existing methods communicate 3D predictions through language tokens, proposal selection, or lightweight grounding queries, creating a bottleneck between language reasoning and dense geometric prediction. Building on these insights, we introduce Qwen-3D, a geometry-aware LMM that compresses visual information within the Qwen backbone using multi-view geometric cues, enabling efficient long-horizon visual reasoning over static scenes. Qwen-3D augments visual tokens with 3D Rotary Positional Embeddings, allowing attention to operate directly in 3D scene space rather than across independent image frames and thereby facilitating scalable cross-view and temporal reasoning. To bridge language and geometry, Qwen-3D incorporates a query-based segmentation decoder that grounds language directly in the underlying 3D scene representation, unifying referential grounding, instance segmentation, and visual question answering across both images and videos. Across a diverse set of benchmarks, Qwen-3D surpasses existing 3D LMMs and outperforms several large proprietary 2D models. Notably, Qwen-3D achieves these improvements while maintaining strong performance on standard 2D vision-language benchmarks by jointly training on 2D and 3D data.

DeepChoice: Learning ViewWeighting for Image-Guided 3D Semantic Segmentation

Abstract. Multi-view image-to-point label transfer is an effective strategy for 3D semantic segmentation, but its performance largely depends on how predictions from multiple image observations are fused for each 3D point. Most existing pipelines rely on hard voting or handcrafted weighting rules, which do not explicitly learn the reliability of each view under varying geometric and image-quality conditions. In this paper, we introduce DeepChoice, a lightweight view-weighting module for image-guided 3D semantic segmentation. For each visible observation of a 3D point, DeepChoice exploits a compact set of visibility cues, including incidence angle, range, contrast, sharpness, signal-to-noise ratio, and saturation, to predict normalized per-view weights used to aggregate 2D semantic class probabilities into final 3D point-wise predictions. The method is sensor-agnostic, requires no meshing, and can be integrated as a replacement for standard multi-view fusion rules. Experiments on the full GridNet-HD benchmark show that DeepChoice improves over hard voting by 3.85 mIoU points and over mean-probability fusion by 1.26 points, while reducing the gap with the AnyView oracle upper bound. The largest gains are observed on thin and difficult classes such as conductors, pylons, and insulators. Furthermore, a complementary evaluation on the Images&PointClouds Cultural Heritage dataset shows that the proposed weighting strategy remains beneficial under a very different acquisition context and scene structure, yielding a 1.55 mIoU point improvement over hard voting. These results show that learning how to weight views is a simple yet effective way to strengthen image-guided 3D semantic segmentation pipelines. Code is publicly available at https://huggingface.co/heig-vd-geo/DeepChoice.