Abstract: Various implementations disclosed herein include devices, systems, and methods that adjust a combined user representation via light normalization techniques. For example, a process may include obtaining a first user representation of at least a first portion of a user generated via a first technique based on the user in a first lighting condition in a first physical environment. The process may further include obtaining a second user representation of at least a second portion of the user, the second user representation being generated by generating and delighting an initial user representation based on a lighting representation of a second physical environment having a second lighting condition, and producing the second user representation by relighting the delighted initial user representation based on the first lighting condition. The process may further include generating combined user representation based on the first user representation and the second user representation.

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide views of a representation based on a proxy representation using three-dimensional Gaussian Splat (3DGS) data. For example, a process may include obtaining 3DGS datasets each using a plurality of splats to represent the object at a respective time associated with a first rate. The process may further include providing a first view depicting the object in a 3D environment corresponding to a first viewpoint. The process may further include generating a proxy representation of the object based on a two-dimensional texture of the first 3DGS dataset. The process may further include providing a second view depicting the object in the 3D environment using the proxy representation from a second viewpoint. The views of the object are generated at a second rate that is faster than the first rate at which the 3DGS data was generated.

Abstract: Various implementations disclosed herein include devices, systems, and methods that adjust a combined user representation via light normalization techniques. For example, a process may include obtaining a first user representation of at least a first portion of a user generated via a first technique based on the user in a first lighting condition in a first physical environment. The process may further include obtaining a second user representation of at least a second portion of the user, the second user representation being generated by generating and delighting an initial user representation based on a lighting representation of a second physical environment having a second lighting condition, and producing the second user representation by relighting the delighted initial user representation based on the first lighting condition. The process may further include generating combined user representation based on the first user representation and the second user representation.

Abstract: Various implementations disclosed herein include devices, systems, and methods that generate a user representation based on selecting a splat rendering approach. For example, a process may include obtaining representation data of at least a portion of an object. The representation data may include data for multiple sets of splats generated based on a splat generation technique. The process may further include determining a context of a viewing experience. The process may further include selecting a splat rendering approach for use in providing a view that includes a representation of the at least the portion of the object based on the determined context of the viewing experience. The process may further include providing a view of a representation of the at least the portion of the object based on the selected splat rendering approach that includes rendering a subset of splats based on the splat parameter data.

Abstract: Various implementations disclosed herein include devices, systems, and methods that generate a user representation based on selecting a subset of splat parameter data. For example, a process may include obtaining user representation data of at least a portion of an object. The representation data may include splat parameter data that define characteristics for splats representing the object. The process may further include selecting a subset of the splats representing the object (e.g., culling the splats) based on a characteristic of a viewing experience. The process may further include providing a view of a representation of the at least the portion of the object based on the selected subset of the splats, where providing the view includes rendering the subset of the splats based on the splat parameter data.

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide a matching skin tone between the hands and the face of a three-dimensional (3D) user representation. For example, a process may obtain at least two skin tones corresponding to colors representing at least two different portions of a hand of a user. In response, a hand texture representing a spatial arrangement of color representing an appearance of the hand is determined. The hand texture may be determined based on the at least two skin tones and hand texture sample data. The process may further include determining a hand structure associated with physical attributes of the hand and the hand structure and the hand texture may be provided for use in generating a 3D representation of the hand.

Abstract: Various implementations disclosed herein include devices, systems, and methods that adjust a combined user representation via light normalization techniques. For example, a process may include obtaining a first user representation of at least a first portion of a user generated via a first technique based on the user in a first lighting condition in a first physical environment. The process may further include obtaining a second user representation of at least a second portion of the user, the second user representation being generated by generating and delighting an initial user representation based on a lighting representation of a second physical environment having a second lighting condition, and producing the second user representation by relighting the delighted initial user representation based on the first lighting condition. The process may further include generating combined user representation based on the first user representation and the second user representation.