105 citations · 248 across the 21 of their papers we have counts for
22 papers
Can Generative Video Models Help Pose Estimation?
Ruojin Cai, Jason Y. Zhang, Philipp Henzler +3
Pairwise pose estimation from images with little or no overlap is an open challenge in computer vision. Existing methods, even those trained on large-scale datasets, struggle in th…
MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
Zhengqi Li, Richard Tucker, Forrester Cole +6
We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional stru…
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
Linyi Jin, Richard Tucker, Zhengqi Li +3
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale superv…
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
Boyang Deng, Richard Tucker, Zhengqi Li +3
We present a method for generating Streetscapes-long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., c…
Shape of Motion: 4D Reconstruction from a Single Video
Qianqian Wang, Vickie Ye, Hang Gao +4
Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effe…
Generative Image Dynamics
Zhengqi Li, Richard Tucker, Noah Snavely +1
We present an approach to modeling an image-space prior on scene motion. Our prior is learned from a collection of motion trajectories extracted from real video sequences depicting…
Tracking Everything Everywhere All at Once
Qianqian Wang, Yen-Yu Chang, Ruojin Cai +4
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence. Prior optical flow or particle video tracking algorithms typically…
Neural-PBIR Reconstruction of Shape, Material, and Illumination
Cheng Sun, Guangyan Cai, Zhengqin Li +6
Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the…
Persistent Nature: A Generative Model of Unbounded 3D Worlds
Lucy Chai, Richard Tucker, Zhengqi Li +2
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of…
DynIBaR: Neural Dynamic Image-Based Rendering
Zhengqi Li, Qianqian Wang, Forrester Cole +2
We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. State-of-the-art methods based on temporally varying Neural Radiance Fi…
InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
Zhengqi Li, Qianqian Wang, Noah Snavely +1
We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single…
Neural 3D Reconstruction in the Wild
Jiaming Sun, Xi Chen, Qianqian Wang +4
We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation a…
3D Moments from Near-Duplicate Photos
Qianqian Wang, Zhengqi Li, David Salesin +3
We introduce 3D Moments, a new computational photography effect. As input we take a pair of near-duplicate photos, i.e., photos of moving subjects from similar viewpoints, common i…
Deformable Sprites for Unsupervised Video Decomposition
Vickie Ye, Zhengqi Li, Richard Tucker +2
We describe a method to extract persistent elements of a dynamic scene from an input video. We represent each scene element as a \emph{Deformable Sprite} consisting of three compon…
IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images
Kai Zhang, Fujun Luan, Zhengqi Li +1
We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material tex…
Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes
Zhengqi Li, Simon Niklaus, Noah Snavely +1
We present a method to perform novel view and time synthesis of dynamic scenes, requiring only a monocular video with known camera poses as input. To do this, we introduce Neural S…
Crowdsampling the Plenoptic Function
Zhengqi Li, Wenqi Xian, Abe Davis +1
Many popular tourist landmarks are captured in a multitude of online, public photos. These photos represent a sparse and unstructured sampling of the plenoptic function for a parti…
UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images
Wenqi Xian, Zhengqi Li, Matthew Fisher +3
We introduce UprightNet, a learning-based approach for estimating 2DoF camera orientation from a single RGB image of an indoor scene. Unlike recent methods that leverage deep learn…
Learning the Depths of Moving People by Watching Frozen People
Zhengqi Li, Tali Dekel, Forrester Cole +4
We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving. Existing methods for recovering depth for dynam…
CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
Zhengqi Li, Noah Snavely
Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data…
Learning Intrinsic Image Decomposition from Watching the World
Zhengqi Li, Noah Snavely
Single-view intrinsic image decomposition is a highly ill-posed problem, and so a promising approach is to learn from large amounts of data. However, it is difficult to collect gro…
MegaDepth: Learning Single-View Depth Prediction from Internet Photos
Zhengqi Li, Noah Snavely
Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the avai…