17 papers
Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
Xi Li, Linyuan Li, Yan Wu +4
Metric feed-forward 3D reconstruction for panoramic data remains under-explored due to the lack of large-scale panoramic RGB-D training data. We present Realsee3D, a hybrid dataset…
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…
E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
Qitao Zhao, Hao Tan, Qianqian Wang +5
Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations…
AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
Bowei Chen, Sai Bi, Hao Tan +6
In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE)…
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Hansheng Chen, Kai Zhang, Hao Tan +3
Few-step diffusion or flow-based generative models typically distill a velocity-predicting teacher into a student that predicts a shortcut towards denoised data. This format mismat…
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…