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 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 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 transfer method that leverages a model trained on a large source dataset to improve the learning ability on small target datasets.
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.
In this paper, we propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations that are fully compatible with the massively parallel graphics rendering pipeline.
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.
The new archetype represents the set of objects using a set of learn- able embeddings, termed as queries, which are fed to a decoder consisting of a stack of decoding stages.
