arXiv AI
HumanSkill-4D: Training-Free Language Querying of Animatable Gaussian Avatars in Space and Time
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 21
STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition
arXiv:2607. 17342v1 Announce Type: cross Abstract: Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision.
arXiv Computer Vision
Oct 16
Fine-grained Human Motion Understanding with Language Models
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.
arXiv Computer Vision
Oct 12
ELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion Generation
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 AI
Jun 30
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
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 Computer Vision
2d ago
R4DGS: Referring Segmentation in 4D Gaussian Splatting
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...
arXiv Computer Vision
6d ago
FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity
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.