57 citations · 67 across the 17 of their papers we have counts for
17 papers
WorldSculpt: Generating Compositional Worlds from Grounded Videos
Muyao Niu, Jixuan He, Ruihan Yu +9
We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects. The goal is to represent the scene as a collection of indi…
WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations
Xiaojie Xu, Zhengyuan Lin, Runyi Li +3
Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene geometry, temporal correspondence and, for interactive models,…
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
Shuo Liang, Yixing Ma, Pengfei Zhou +33
Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial risks of misinformation. Existi…
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li +15
This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged from the pr…
Sekai2: From World Exploration to Interactive World Modeling
Kang He, Wenshuo Peng, Zihui Gao +3
Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefore benefits from long videos…
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li +15
Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interac…
AlayaWorld: Long-Horizon and Playable Video World Generation
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li +14
Game worlds have traditionally been built through labor-intensive production pipelines, making them costly to develop, difficult to customization, and expensive to modify after dep…
WorldMark: A Unified Benchmark Suite for Interactive Video World Models
Xiaojie Xu, Zhengyuan Lin, Kang He +5
Unlike text- or image-driven video generation, an interactive world model is driven by actions: the user acts, and the world responds. Two obstacles stand in the way of fair and co…
Generative Video Matting
Yongtao Ge, Kangyang Xie, Guangkai Xu +6
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and fo…
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
Songyan Zhang, Yongtao Ge, Jinyuan Tian +4
3D reconstruction in dynamic scenes primarily relies on the combination of geometry estimation and matching modules where the latter task is pivotal for distinguishing dynamic regi…
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
Yongtao Ge, Guangkai Xu, Zhiyue Zhao +5
Recent advances in discriminative and generative pretraining have yielded geometry estimation models with strong generalization capabilities. While discriminative monocular geometr…
Diffusion Models are Efficient Data Generators for Human Mesh Recovery
Yongtao Ge, Wenjia Wang, Yongfan Chen +4
Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor moc…
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
Guangkai Xu, Yongtao Ge, Mingyu Liu +5
Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent…
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
Wenjia Wang, Yongtao Ge, Haiyi Mei +6
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based…
Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations
Yongtao Ge, Qiang Zhou, Xinlong Wang +3
Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object…
Poseur: Direct Human Pose Regression with Transformers
Weian Mao, Yongtao Ge, Chunhua Shen +4
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transf…
TFPose: Direct Human Pose Estimation with Transformers
Weian Mao, Yongtao Ge, Chunhua Shen +3
We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-…