|
Generating 3D-Consistent Videos from Unposed Internet Photos
Gene Chou, Kai Zhang, Sai Bi, Hao Tan, Zexiang Xu, Fujun Luan, Bharath Hariharan, Noah Snavely
Arxiv 2024
paper / project page
We propose the task of generating videos from sparse, unposed internet photos,
and design a self-supervised method that takes advantage of the consistency of videos and
variability of multiview internet photos to train a 3D-aware video model without any 3D annotations such as camera parameters.
|
|
MegaScenes: Scene-Level View Synthesis at Scale
Joseph Tung*, Gene Chou*, Ruojin Cai, Guandao Yang, Kai Zhang, Gordon Wetzstein, Bharath Hariharan, Noah Snavely
ECCV 2024
paper / code / project page
MegaScenes is a scene-level dataset containing 100K SfM reconstructions and 2M registered images, collected from Wikimedia Commons.
We validate its effectiveness in training large-scale, generalizable models on the task of single image novel view synthesis.
|
|
Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models
Hung-Shuo Chang, Chien-Yao Wang, Richard Wang, Gene Chou, Hong-Yuan Mark Liao
WACV 2025
paper
Builds on YOLOR to jointly train vision (e.g. object detection, instance and semantic segmentation) and vision-language (e.g. image captioning) tasks. Fast and lightweight while achieving competitive performance.
|
|
Thin On-Sensor Nanophotonic Array Cameras
Praneeth Chakravarthula, Jipeng Sun, Xiao Li, Chenyang Lei, Gene Chou, Mario Bijelic, Johannes Froesch, Arka Majumdar, Felix Heide
SIGGRAPH ASIA 2023
paper / project page
Recovers images in broadband using a single flat metasurface optic. Compensates for residual aberrations with probabilistic deconvolution implemented using a conditional diffusion model.
|
|
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
Gene Chou, Yuval Bahat, Felix Heide
ICCV 2023
paper / code / project page
Performs diffusion on the latent space of neural SDFs while providing geometric guidance. Generates diverse meshes conditioned on partial point clouds, 2D images, and real-scanned, noisy point clouds.
|
|
GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions
Gene Chou, Ilya Chugunov, Felix Heide
NeurIPS 2022
paper / code / project page
Combines a semi-supervised approach with a self-supervised loss to reconstruct neural SDFs from raw input point clouds of over a hundred unseen object classes.
|
|