activity
20242026
collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

RayZer: A Self-supervised Large View Synthesis Model

Hanwen Jiang, Hao Tan, Peng Wang +8

We present RayZer, a self-supervised multi-view 3D Vision model trained without any 3D supervision, i.e., camera poses and scene geometry, while exhibiting emerging 3D awareness. C…

cs.CV2025

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

Haian Jin, Hanwen Jiang, Hao Tan +6

We propose the Large View Synthesis Model (LVSM), a novel transformer-based approach for scalable and generalizable novel view synthesis from sparse-view inputs. We introduce two a…