arXiv:2607. 17342v1 Announce Type: cross Abstract: Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision.
Fine-grained Human Motion Understanding with Language Models introduces FiGMo, an LLM-based model that represents motion as timestamp‑grounded skeletal poses, enabling reasoning over action order and duration. The model uses a unified pose encoder for both 2D and 3D skeletons, optionally incorporating RGB context, and relies on newly constructed pose‑to‑motion supervision to address limited pose‑level grounding. Experiments demonstrate that timestamps improve temporal localization and preserve physical timing under subsampling, leading FiGMo to achieve state‑of‑the‑art results on motion question answering, dense motion captioning, and action recognition with detected poses.
The paper introduces ELMA, a new episodic long‑term motion dataset designed to benchmark anaphoric compositions in text‑to‑motion generation. ELMA contains densely annotated 30‑second clips extracted from in‑the‑wild videos, preserving cross‑segment dependencies that current models struggle to handle. Fine‑tuning state‑of‑the‑art models on ELMA improves both global physical realism and semantic alignment, establishing a robust baseline for long‑term motion synthesis.
arXiv:2606. 29531v1 Announce Type: cross Abstract: We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs.
arXiv:2610.30326v1 Announce Type: new Abstract: Dynamic representations based on 4D Gaussian Splatting (4DGS) have shown strong capabilities in reconstruction and rendering, yet current methods remai...
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.
Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and the habits of the people who live in it. Progre...
arXiv:2609.25832v1 Announce Type: new Abstract: Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies,...
arXiv:2610.10438v1 Announce Type: new Abstract: Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment an...
arXiv:2501.04001v4 Announce Type: replace Abstract: This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-...
arXiv:2604. 22160v2 Announce Type: replace-cross Abstract: Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation.
MoRE introduces a Motion-Regularized Encoding for generating articulated 3D objects from a single image. It encodes joint attributes as coordinate‑aligned joint lines with axis classification and Plücker moment coefficients, and couples attribute reconstruction to motion through a differentiable expectation over joint types and axis directions. Experiments on PartNet‑Mobility and ACD demonstrate improved part‑box agreement, articulated‑state geometry, visual similarity, and reduced joint prediction errors compared to prior methods.