Propose a framework based on diffusion models for consistent and realistic long-term novel view synthesis. Diffusion models have achieved impressive performance on many content creation applications, such as image-to-image translation and text-to- image generation.
We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with...
Recognizing human activities is a decades-old problem in computer vision. With recent advancements in user- assistive augmented reality and virtual reality (AR/VR) systems...
We introduce RoDynRF, an algorithm for reconstructing dynamic radiance fields from casual videos. Unlike existing approaches, we do not require accurate camera poses as input. Our method optimizes camera poses and two radiance fields, modeling static and dynamic elements. Our approach includes a coarse-to-fine strategy and epipolar geometry to exclude moving pixels, deformation fields, time- dependent appearance models, and regularization losses for improved consistency.
We propose a model, called Cube R-CNN, designed to generalize across camera and scene types with a unified approach. We show that Cube R-CNN outperforms prior works on the larger...
We explore egocentric audio-visual object localization task and observe that egomotion commonly exists in first-person recordings and out-of-view sound components can be created.
We propose a transfer method that leverages a model trained on a large source dataset to improve the learning ability on small target datasets.
In this work, we argue that the egocentric perspective offers an opportunity for holistic perception that can beneficially leverage synergies among video tasks to solve all...
In this work, we propose a 3D compositional morphable model of eyeglasses that accurately incorporates high-fidelity geometric and photometric interaction effects.
We introduce a simple framework that operates on 3D points of single objects or whole scenes coupled with category-agnostic largescale training from diverse RGB-D videos.
