Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
SAM‑V is a geometry‑aware extension of the Segment Anything Model (SAM) that integrates 3D priors from a feed‑forward geometry model (VGGT) into 2D segmentation. It uses a prompt‑fusion mechanism to combine sparse SAM prompts with view‑specific camera tokens and local VGGT features, enabling a mask decoder that attends to both dense 2D and 3D cues. The resulting end‑to‑end system produces consistent multi‑view instance segmentation in a single forward pass, achieving significant gains on the IGGT 3D tracking benchmark without offline mask matching or explicit 3D reconstruction.
arXiv:2608.18734v2 Announce Type: replace Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vis...
arXiv:2608.30451v1 Announce Type: new Abstract: Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect tempo...
arXiv:2606. 31148v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions.
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.
TempoGround is a vision‑language model–native framework for streaming visual grounding that detects cross‑frame object correspondence and explicitly models object presence states. It uses a curriculum prediction mechanism to resolve 2D instance association, predict object entry, continuation, or exit, decode 2D boxes, and lift them to 3D camera‑frame boxes. The approach is further refined with Streaming Grounding Reinforcement, which optimizes grounding, identity, and consistency rewards, and achieves significant improvements on multiple streaming visual grounding benchmarks.
arXiv:2606. 00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains underexplored.
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image ca...
arXiv:2512. 23020v3 Announce Type: replace-cross Abstract: 3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes.
arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.
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.