1 citations · 3 across the 25 of their papers we have counts for
22 papers · 1 filter
LLM2R: From Large Language Models to 3D Reassemblers
Zhouhan Zhong, Qiuhong Shen, Xingyi Yang +2
3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a part is r…
Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes
Hanyang Kong, Xingyi Yang
Understanding interaction in a 3D scene requires recovering movable parts, their motion, and where they can be operated. These quantities are related, and their predictions can inf…
Visual Geometry Transformer in the Wild: Distractor-Free 3D Reconstruction
Tianbo Pan, Xingyi Yang, Shizun Wang +1
Current end-to-end multi-view 3D reconstruction methods achieve impressive results, but rely on a restrictive static assumption: the scenes is entire distractor-free with perfect c…
BadWorld: Adversarial Attacks on World Models
Linghui Shen, Mingyue Cui, Xingyi Yang
Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adve…
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
Siao Tang, Xinyin Ma, Gongfan Fang +2
Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time interactive video generation and…
ReactiveGWM: Flexible Control and NPC Reactivity in Game World Models
Zeqing Wang, Danze Chen, Zhaohu Xing +4
Existing game world models typically adopt role-specific interactions, where player and NPC roles are bound to fixed characters. This limits their flexibility in multi-character ga…
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
Yuhang Dai, Xingyi Yang
Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually…
WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
Hanyang Kong, Xingyi Yang, Xiaoxu Zheng +1
Generating long-range, geometrically consistent video presents a fundamental dilemma: while consistency demands strict adherence to 3D geometry in pixel space, state-of-the-art gen…
DeContext as Defense: Safe Image Editing in Diffusion Transformers
Linghui Shen, Mingyue Cui, Xingyi Yang
In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily ma…
Vision Bridge Transformer at Scale
Zhenxiong Tan, Zeqing Wang, Xingyi Yang +2
We introduce Vision Bridge Transformer (ViBT), a large-scale instantiation of Brownian Bridge Models designed for conditional generation. Unlike traditional diffusion models that t…
C4D: 4D Made from 3D through Dual Correspondences
Shizun Wang, Zhenxiang Jiang, Xingyi Yang +1
Recovering 4D from monocular video, which jointly estimates dynamic geometry and camera poses, is an inevitably challenging problem. While recent pointmap-based 3D reconstruction m…
Test3R: Learning to Reconstruct 3D at Test Time
Yuheng Yuan, Qiuhong Shen, Shizun Wang +2
Dense matching methods like DUSt3R regress pairwise pointmaps for 3D reconstruction. However, the reliance on pairwise prediction and the limited generalization capability inherent…
Image Editing As Programs with Diffusion Models
Yujia Hu, Songhua Liu, Zhenxiong Tan +2
While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highl…
Minute-Long Videos with Dual Parallelisms
Zeqing Wang, Bowen Zheng, Xingyi Yang +3
Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos. To address…
Flash Sculptor: Modular 3D Worlds from Objects
Yujia Hu, Songhua Liu, Xingyi Yang +1
Existing text-to-3D and image-to-3D models often struggle with complex scenes involving multiple objects and intricate interactions. Although some recent attempts have explored suc…
1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering
Yuheng Yuan, Qiuhong Shen, Xingyi Yang +1
4D Gaussian Splatting (4DGS) has recently gained considerable attention as a method for reconstructing dynamic scenes. Despite achieving superior quality, 4DGS typically requires s…
OminiControl2: Efficient Conditioning for Diffusion Transformers
Zhenxiong Tan, Qiaochu Xue, Xingyi Yang +2
Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment. While recent advances such as OminiControl and other…
Neural Metamorphosis
Xingyi Yang, Xinchao Wang
This paper introduces a new learning paradigm termed Neural Metamorphosis (NeuMeta), which aims to build self-morphable neural networks. Contrary to crafting separate models for di…
Vista3D: Unravel the 3D Darkside of a Single Image
Qiuhong Shen, Xingyi Yang, Michael Bi Mi +1
We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts. To address this, we present Vista3D, a framework that realizes…
Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
Bonan Li, Zicheng Zhang, Xingyi Yang +1
Generating dense multiview images from text prompts is crucial for creating high-fidelity 3D assets. Nevertheless, existing methods struggle with space-view correspondences, result…
Video-Infinity: Distributed Long Video Generation
Zhenxiong Tan, Xingyi Yang, Songhua Liu +1
Diffusion models have recently achieved remarkable results for video generation. Despite the encouraging performances, the generated videos are typically constrained to a small num…
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Songhua Liu, Xin Jin, Xingyi Yang +2
Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging…