Lemon Inc.

Qingyu Chen

Peilin Li

Xiaojie Li

Yuxi Zhang

Tianyang Xu

Xing Mei

Yunzhu Li

Haoze Li

Celong Liu

Lelin Zhang

A computer-implemented method for transforming a neural radiance field model is described. A plurality of inputs are provided to a neural radiance field (NeRF) model that represents a 3-dimensional space having a subject, wherein each input of the plurality of inputs includes a location and a view direction and corresponds to respective colors of voxels that represent the 3-dimensional space. A spectral analysis is performed on a plurality of outputs of the NeRF model based on the plurality of inputs, wherein the plurality of outputs include the respective colors of the voxels. Frequency components of the spectral analysis that represent colors for at least some of the voxels are extracted. A sparse volume data structure that represents the 3-dimensional space and the respective colors for the at least some of the voxels is generated.

View synthesis from sparse volume data structure

The present disclosure describes techniques for social networking based on collecting asset items. Features may be extracted from an image comprising an object and captured by a camera. The object may be associated with a location. The location may be determined based on information indicating a position where the camera is located. The object may be recognized based at least in part on the features extracted from the image. An asset item may be displayed in response to recognizing the object.

Social networking based on collecting asset items

The present disclosure describes techniques for social networking based on trading asset items. The techniques comprise sending a request by a first client computing device for connecting with a second client computing device, displaying a first video comprising a first user and a second video comprising a second user on an interface, determining a first body part of the first user based on a selection of a representative of a first asset item associated with the second user, determining a position of rendering an image of the first asset item on the interface, rendering the image of the first asset item and combining the image into the first video for display of an effect of the first asset item being tried on the first body part of the first user, and receiving the first asset item from the second user based on the effect and user input.

Social networking based on asset items

Embodiments of the present disclosure provide an end-cloud collaborative media data processing method and apparatus, a device and a storage medium, where the method includes: calling a target processing flow in response to a first operation triggering a target functionality, where the target processing flow includes a local algorithm node and a remote algorithm node, and the target functionality is used for adding a special effect to media data to be processed; executing, based on the target processing flow, a corresponding local algorithm node and remote algorithm node to obtain first processing data output by the local algorithm node and second processing data output by the remote algorithm node; and generating third processing data through the first processing data and/or the second processing data.

Growing community of inventors

Los Angeles, CA, United States of America

Qingyu Chen