SplatScout is a new query‑driven, closed‑loop approach for part‑level referring segmentation in Gaussian scenes, placing perception under vision‑language model control. It actively selects views, directs segmentation, and refines predictions by inspecting rendered 3D results. On the newly introduced PartRef‑ScanNet++ benchmark, SplatScout achieves 0.538 mIoU, outperforming existing methods and demonstrating the benefits of iterative refinement and effective tool‑feedback utilization.
Recent advancements in 3D Gaussian Splatting (3DGS) have enabled language-guided scene understanding. However, existing Referring 3D Gaussian Splatting (R3DGS) methods are fundamentally restricted to single-target queries.
SetCon reformulates open-ended referring segmentation as set-level concept prediction, using LVLM-generated natural-language concepts instead of segmentation-specific tokens. It employs a hierarchical semantic decomposition that first predicts a shared set-level concept and then refines it into fine-grained concept groups aligned with target subsets. The method, supported by a two-stage annotation pipeline adding hierarchical semantic supervision, achieves state-of-the-art results on multiple image and video benchmarks, with performance gains increasing as the number of referred targets grows.
The paper introduces R4DGS, a method for referring segmentation in dynamic 4D Gaussian splatting scenes. It presents the R4D-Bench-QA benchmark with structured query annotations and a unified framework called ReferGaussian that converts dynamic Gaussians into language-addressable entities for training‑free inference. Experiments show improved temporal target selection and competitive spatiotemporal grounding without scene‑specific semantic training.
The paper examines how rewriting verbose, narrative-style queries into concise keyword‑grounded forms improves complex object segmentation in 4D Gaussian representations. By applying a training‑free reinterpretation strategy, the authors reduce linguistic noise while preserving essential semantic anchors. Experiments on HyperNeRF and Neu3D show that rewritten queries boost temporal accuracy from 60.92% to 92.21% and vIoU from 20.08% to 76.94%, with ablation studies confirming the benefits of shorter, keyword‑focused queries.
arXiv:2610.24452v2 Announce Type: replace-cross Abstract: We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also spec...
FoRIS is a training‑free in‑context segmentation framework that refines foreground masks through a coarse‑to‑fine process. It operates in three stages—Foreground Purification, Localization, and Consolidation—to suppress background noise, pinpoint target regions, and reconstruct complete foreground structures. The method achieves state‑of‑the‑art performance, improving mIoU by 4.5 and 4.8 points in 1‑shot and 5‑shot settings respectively.
FlexPart is a new framework that enables text‑controlled, semantics‑aware 3D mesh segmentation at any desired granularity. It introduces a holistic control prompt that combines part names with location and shape clauses, and uses a Vision‑Language Model pipeline to generate a large multi‑granularity dataset. The model produces a view‑independent part‑identity field in 3D space, and an inference‑time VLM planner can auto‑complete descriptive clauses from 2D renderings, allowing users to specify parts with ordinary words. FlexPart outperforms strong baselines by up to 22% in mIoU on its benchmark and improves selective segmentation by 35% over click‑driven methods.
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...
PANORAMA introduces a new panoptic grounded captioning framework that jointly generates detailed image captions and associates each phrase with precise pixel-level masks. The authors create PanoCaps, a human‑annotated benchmark with dense captions and near‑complete pixel coverage, and propose a phrase‑mask matching protocol with a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations, learns to select appropriate masks, and achieves state‑of‑the‑art grounding performance on PanoCaps and other pixel‑level tasks.
SOCO is a new benchmark for Semantic Object Correspondence that introduces a taxonomy of correspondence types and provides consistent, functionally meaningful keypoint annotations across 100 categories and over 1M correspondence pairs. It also includes keypoint language descriptions, enabling evaluation of large vision‑language models and their fine‑grained part‑level understanding. Experiments show that vision foundation backbones encode strong semantic structure but transfer correspondences poorly across related categories, LVLMs excel at text‑prompted part localization but lag in visual‑reference matching, and correspondence performance predicts dense downstream tasks more strongly than ImageNet classification.
arXiv:2606. 28149v1 Announce Type: cross Abstract: In-context segmentation (ICS) requires a model to segment target regions in a query image using only a few reference images and their corresponding masks, without updating any parameters.
arXiv:2610.20352v1 Announce Type: new Abstract: Multimodal Large Language Models have made significant progress in referring expression comprehension (REC), yet most REC benchmarks still focus on fin...