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 …
Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging. Recently, differentiable rendering provides a pathway to …
J Tan, G Yang, D Ramanan - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
We present a method for reconstructing articulated 3D models from videos in real-time, without test-time optimization or manual 3D supervision at training time. Prior work often …
Training a 3D human keypoint detector from point clouds in a supervised manner requires large volumes of high quality labels. While it is relatively easy to capture large amounts of …
Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials …
Single-view RGB-D human reconstruction with implicit functions is often formulated as per- point classification. Specifically, a set of 3D locations within the view-frustum of the camera …
S Liu, S Gupta, S Wang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
We build rearticulable models for arbitrary everyday man-made objects containing an arbitrary number of parts that are connected together in arbitrary ways via 1-degree-of …
Abstract We present Bayesian Diffusion Models (BDM) a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the …
Animating an object in 3D often requires an articulated structure, eg a kinematic chain or skeleton of the manipulated object with proper skinning weights, to obtain smooth …