Publications (14)
Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking
Yiheng Liu, Junta Wu, Yi Fu
Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer…
Pathwise Test-Time Correction for Autoregressive Long Video Generation
Xunzhi Xiang, Zixuan Duan, Guiyu Zhang +7
Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-…
OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
Yanqin Jiang, Tengfei Wang, Zhengwei Wang +6
Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited t…
WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
Yisu Zhang, Chenjie Cao, Tengfei Wang +4
Recent advances in foundational Video Diffusion Models (VDMs) have yielded significant progress. Yet, despite the remarkable visual quality of generated videos, reconstructing cons…
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Wenqiang Sun, Haiyu Zhang, Haoyuan Wang +7
This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off be…
Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
Xianghui Yang, Huiwen Shi, Bowen Zhang +20
While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address…
Large Point-to-Gaussian Model for Image-to-3D Generation
Longfei Lu, Huachen Gao, Tao Dai +4
Recently, image-to-3D approaches have significantly advanced the generation quality and speed of 3D assets based on large reconstruction models, particularly 3D Gaussian reconstruc…
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Team HY-World, Chenjie Cao, Xuhui Zuo +42
We introduce HY-World 2.0, a multi-modal world model framework that advances our prior project HY-World 1.0. HY-World 2.0 accommodates diverse input modalities, including text prom…
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Zibo Zhao, Zeqiang Lai, Qingxiang Lin +71
We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-sca…
WorldCompass: Reinforcement Learning for Long-Horizon World Models
Zehan Wang, Tengfei Wang, Haiyu Zhang +9
This work presents WorldCompass, a novel Reinforcement Learning (RL) post-training framework for the long-horizon, interactive video-based world models, enabling them to explore th…
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
HunyuanWorld Team, Zhenwei Wang, Yuhao Liu +52
Creating immersive and playable 3D worlds from texts or images remains a fundamental challenge in computer vision and graphics. Existing world generation approaches typically fall…
MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
Zhiqi Li, Wenhuan Li, Tengfei Wang +8
Compositionality is critical for 3D object and scene generation, but existing part-aware 3D generation methods suffer from poor scalability due to quadratic global attention costs…
Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
Tianyu Huang, Wangguandong Zheng, Tengfei Wang +8
Real-world applications like video gaming and virtual reality often demand the ability to model 3D scenes that users can explore along custom camera trajectories. While significant…
WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
Yifan Liu, Zhiyuan Min, Zhenwei Wang +5
We present WorldMirror, a unified feed-forward model for comprehensive 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a s…