15 citations · 42 across the 19 of their papers we have counts for
22 papers
IronMind: Scaling Humanoid Dexterous Manipulation via Camera-Space Ego-Centric Pretraining
Huimin Pan, Yufan Ren, Kunpeng Song +16
Egocentric human video offers a scalable data source for dexterous manipulation, yet using it to train humanoid robots presents two challenges: (1) an embodiment gap, as human hand…
XPACE: Joint World and Action Modeling from Heterogeneous Experience
Jiacheng Wei, Jerry Bai, Xiaoyu Yue +13
A general-purpose robot needs to draw on diverse experience, choose actions, and anticipate how those actions will change the world. We introduce XPACE, a unified embodied world mo…
AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization
Cheng Chen, Jerry Bai, Jiacheng Wei +11
Collecting contact-rich robot experiences at scale remains a major bottleneck for generalizable manipulation. Beyond data quantity, robot learning also requires diverse experiences…
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
Youtan Yin, Yanning Zhou, Jiacheng Wei +6
Local editing of 3D objects remains a long-standing challenge. When interacting with 3D content, humans naturally tend to specify a coarse region of interest for modification rathe…
PhyCustom: Towards Realistic Physical Customization in Text-to-Image Generation
Fan Wu, Cheng Chen, Zhoujie Fu +4
Recent diffusion-based text-to-image customization methods have achieved significant success in understanding concrete concepts to control generation processes, such as styles and…
IC-World: In-Context Generation for Shared World Modeling
Fan Wu, Jiacheng Wei, Ruibo Li +4
Video-based world models have recently garnered increasing attention for their ability to synthesize diverse and dynamic visual environments. In this paper, we focus on shared worl…
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation
Zhoujie Fu, Xianfang Zeng, Jinghong Lan +9
Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often co…
Puppeteer: Rig and Animate Your 3D Models
Chaoyue Song, Xiu Li, Fan Yang +6
Modern interactive applications increasingly demand dynamic 3D content, yet the transformation of static 3D models into animated assets constitutes a significant bottleneck in cont…
OccLE: Label-Efficient 3D Semantic Occupancy Prediction
Naiyu Fang, Zheyuan Zhou, Fayao Liu +5
3D semantic occupancy prediction offers an intuitive and efficient scene understanding and has attracted significant interest in autonomous driving perception. Existing approaches…
CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images
Cheng Chen, Jiacheng Wei, Tianrun Chen +8
Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-in…
Prim2Room: Layout-Controllable Room Mesh Generation from Primitives
Chengzeng Feng, Jiacheng Wei, Cheng Chen +5
We propose Prim2Room, a novel framework for controllable room mesh generation leveraging 2D layout conditions and 3D primitive retrieval to facilitate precise 3D layout specificati…
Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
Zhoujie Fu, Jiacheng Wei, Wenhao Shen +5
In this work, we introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos. Our method transfers the motion o…
REACTO: Reconstructing Articulated Objects from a Single Video
Chaoyue Song, Jiacheng Wei, Chuan-Sheng Foo +2
In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video. Existing works employing dynamic neural radiance fields have advanced…
Learning-Based Biharmonic Augmentation for Point Cloud Classification
Jiacheng Wei, Guosheng Lin, Henghui Ding +2
Point cloud datasets often suffer from inadequate sample sizes in comparison to image datasets, making data augmentation challenging. While traditional methods, like rigid transfor…
MoDA: Modeling Deformable 3D Objects from Casual Videos
Chaoyue Song, Jiacheng Wei, Tianyi Chen +4
In this paper, we focus on the challenges of modeling deformable 3D objects from casual videos. With the popularity of neural radiance fields (NeRF), many works extend it to dynami…
TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
Jiacheng Wei, Hao Wang, Jiashi Feng +2
In this paper, we investigate an open research task of generating controllable 3D textured shapes from the given textual descriptions. Previous works either require ground truth ca…
Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction
Chaoyue Song, Jiacheng Wei, Ruibo Li +2
The goal of 3D pose transfer is to transfer the pose from the source mesh to the target mesh while preserving the identity information (e.g., face, body shape) of the target mesh.…
Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision
Shichao Dong, Ruibo Li, Jiacheng Wei +2
Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas. However, most existing meth…
Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation
Shi Hanyu, Wei Jiacheng, Wang Hao +2
LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame…
3D Pose Transfer with Correspondence Learning and Mesh Refinement
Chaoyue Song, Jiacheng Wei, Ruibo Li +2
3D pose transfer is one of the most challenging 3D generation tasks. It aims to transfer the pose of a source mesh to a target mesh and keep the identity (e.g., body shape) of the…
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds
Jiacheng Wei, Guosheng Lin, Kim-Hui Yap +2
Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address…
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
Jiacheng Wei, Guosheng Lin, Kim-Hui Yap +2
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labe…