Xingang Pan
@XingangP
Followers
3K
Following
322
Media
21
Statuses
75
Assistant Professor at Nanyang Technological University @NTUsg @MMLabNTU - Computer Vision, Deep Learning, Computer Graphics
Singapore
Joined May 2018
Cool work that connects the idea of volume rendering with image diffusion!.
Our paper LaRender received full marks at ICCV 2025 and was selected as oral! This paper enables control of occlusion relationships among objects and visual effects in a training-free manner for diffusion-based image generation. Project page:
0
0
0
The most fun image & video creation tool in the world is here. Try it for free in the Grok App.
0
37
338
Introducing ๐ฆ๐ง๐ฟ๐ฒ๐ฎ๐บ๐ฏ๐ฅ, a new 3D geometric foundation model for efficient 3D reconstruction from streaming input. Similar to LLMs, STream3R uses casual attention during training and KVCache at inference. No need to worry about post-alignment or reconstructing from scratch.
๐ฅStreaming-based 3D/4D Foundation Model๐ฅ. We present STream3R, which reformulates dense 3D/4D reconstruction into a sequential registration task with **causal attention**. - Projects: - Code: - Model:
4
16
92
Directly training Video Diffusion Models on long videos faces huge memory and learning challenges. How do we model long-range temporal distribution then?. Our ICCV 2025 work, ๐๏ธ๐ง๐ผ๐ธ๐ฒ๐ป๐๐๐ฒ๐ป, offers a solution. We compress videos into a highly condensed token space, enabling
0
24
102
๐ช๐ผ๐ฟ๐น๐ฑ๐ ๐ฒ๐บ is mainly created by @zeqi_xiao .Project page: ArXiv: Github: Demo:
1
0
4
Synthesizing worlds with video diffusion models is often inconsistent โ moving the camera back and forth leads to different scenes. We propose ๐๐ช๐ผ๐ฟ๐น๐ฑ๐ ๐ฒ๐บ, a memory-based approach that ensures consistent world simulation without relying on explicit 3D reconstruction.
While recent works like Genie 2, The Matrix, and Navigation World Models explore video generative models as world simulators, world consistency remains underexplored. In this work, we propose ๐WorldMem๐, introducing a memory mechanism for long-term consistent world simulation.
2
26
148
The Bokeh Effect is so important in photography, yet existing text2image diffusion models do not support controling bokeh strength. We introduce ๐๐ผ๐ธ๐ฒ๐ต ๐๐ถ๐ณ๐ณ๐๐๐ถ๐ผ๐ป, a T2I diffusion model that supports flexible background blur control!. Project:
1
9
43
RT @TheYihangLuo: ๐ฅ Consistent Multi-View Diffusion for 3D Enhancement ๐ฅ. Introducing our work #3DEnhancer @CVPR: a multi-view diffusion moโฆ.
0
9
0
RT @zeqi_xiao: Introducing ๐กTrajectory Attention for Fine-grained Video Motion Control๐ก. By augmenting attention along predefined trajectorโฆ.
0
10
0
Introducing ๐๐๐๐๐, which tokenizes 3D objects into multiscale tokens and generates 3D objects by autoregressive next-scale prediction. ๐๐๐๐๐ enables fast 3D generation and comprehensive 3D understanding. arXiv: Project:
2
51
239
Introducing ๐๐๐ฎ๐ฌ๐ฌ๐ข๐๐ง ๐๐ง๐ฒ๐ญ๐ก๐ข๐ง๐ , a new 3D generative model with two key properties:.- A structured point-cloud latent space enabling flexible editing!.- Support multi-modal conditions, e.g., point cloud, text, single/multi-view images. arXiv:
9
49
301
Can we drag 3D objects with large structure changes, like what we can do with DragGAN? .Our work ๐ค๐๐๐๐ซ๐๐ ๐๐๐ฆ makes this possible. Now you can open a lion's mouth or spread a bird's wings in 3D!. arXiv: Project:
1
28
141