13 papers
KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos
Gene Chou, Kai Zhang, Sai Bi +5
We address the problem of generating videos from unposed internet photos. A handful of input images serve as keyframes, and our model interpolates between them to simulate a path m…
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
Yuanhao Cai, He Zhang, Kai Zhang +12
Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt…
Gaussian Mixture Flow Matching Models
Hansheng Chen, Kai Zhang, Hao Tan +5
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However,…
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
Chen Ziwen, Hao Tan, Kai Zhang +5
We propose Long-LRM, a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360° wide-coverage, scene-level reconstruction. Specifically, it takes in 32 inp…
RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
Ziqi Pang, Tianyuan Zhang, Fujun Luan +5
We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a p…
Test-Time Training Done Right
Tianyuan Zhang, Sai Bi, Yicong Hong +6
Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent sta…