Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Abstract 3D reconstruction of deformable (or non‐rigid) scenes from a set of monocular 2D
image observations is a long‐standing and actively researched area of computer vision and …

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 …

Abstract Training a Neural Radiance Field (NeRF) without pre-computed camera poses is
challenging. Recent advances in this direction demonstrate the possibility of jointly …

Test-time training adapts to a new test distribution on the fly by optimizing a model for each
test input using self-supervision. In this paper, we use masked autoencoders for this one …

We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM
consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense …

Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-
term quest. The task is especially appealing when only a few or even single RGB cameras …

We present an algorithm for reconstructing the radiance field of a large-scale scene from a
single casually captured video. The task poses two core challenges. First, most existing …

We present a method for text-driven perpetual view generation--synthesizing long-term
videos of various scenes solely, given an input text prompt describing the scene and camera …

In this work, we present a new multi-view depth estimation method that utilizes both
conventional SfM reconstruction and learning-based priors over the recently proposed …