In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a...
Xun Cai, Rui-Jie Zhu, Hao-Liang Shang et al.· 0 citations
LIME is proposed, a vision-language camera-motion generator that combines an autoregressive observation-gain output with a continuous flow-matching pose head that learns intent-conditioned camera motion from passive egocentric video, turning ordinary human recordings into supervision for a reusable active-perception pr...
Bo-Yang Sun, Jiajie Li, Yung-Hsu Yang et al.· arXiv.org· 3 citations
MoMa-SG, a novel framework for building semantic-kinematic 3D scene graphs of articulated scenes containing a myriad of interactable objects, and the Arti4D-Semantic dataset, which provides parent-child relation annotations between container and contained objects together with object axis annotations across 62 in-the-w...
Martin Buchner, Adrian Rofer, Tim Engelbracht et al.· arXiv.org· 12 citations
Current 3D generation methods lack explicit local control: geometric adherence is often defined by a global control strength, and appearance cannot be specified locally. We present SpaceFlow, a training-free pipeline for locally controllable 3D generation from text descriptions and a collection of geometric primitives....
Neil De La Fuente, Joan Lafuente, Mukhammadali Sayfiddinov et al.· 0 citations
This work introduces a benchmark of 20 real scenes, from coherent streams to violent splashes, captured by seven synchronized, calibrated 4K cameras at 60 fps, with manually refined per-view liquid and container masks and fixed evaluation splits, and presents SplashSplat, built on a single principle: impose physical st...
Pei-Yu Liu, Ding-Xi Zhang, Federico Tombari et al.· 0 citations
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evidence across viewpoints into a coherent 3D understanding. A growing body of work attempts to close th...
Jaewoo Jung, Hyeonseo Yu, Honggyu An et al.· 0 citations
This work introduces EgoTrack3D, a modular framework that reconstructs and maintains a dynamic 3D scene representation directly from egocentric RGB video, and replaces dense depth maps with sparse 3D bounding box estimation and integrate interaction-guided dynamic association, enabling EgoTrack3D to maintain accurate s...
Jan Kulik, Bjarni Dagur Thor Karason, Yung-Hsu Yang et al.· 0 citations
ForceTwin is a system for identifying physics-informed digital twins of articulated objects from instrumented human interaction that achieves 87% goal completion across nine object-embodiment pairs, compared with 60% using VLM-prior and 57% using kinematics-only twins.
Tim Engelbracht, René Zurbrügg, Mayank Mittal et al.· 0 citations
Map-Det3D is an online multi-view 3D object detection model that brings detection directly into a 3D space reconstructed from RGB, suggesting that training reconstruction priors for detection is a practical route to stable metric 3D detection from monocular video.
Yung-Hsu Yang, Luigi Piccinelli, S. R. Bulò et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
