PRIF: Primary Ray-based Implicit Function

08/12/2022
by   Brandon Yushan Feng, et al.
7

We introduce a new implicit shape representation called Primary Ray-based Implicit Function (PRIF). In contrast to most existing approaches based on the signed distance function (SDF) which handles spatial locations, our representation operates on oriented rays. Specifically, PRIF is formulated to directly produce the surface hit point of a given input ray, without the expensive sphere-tracing operations, hence enabling efficient shape extraction and differentiable rendering. We demonstrate that neural networks trained to encode PRIF achieve successes in various tasks including single shape representation, category-wise shape generation, shape completion from sparse or noisy observations, inverse rendering for camera pose estimation, and neural rendering with color.

READ FULL TEXT

page 8

page 13

page 14

page 21

page 23

page 24

page 32

page 33

research
11/29/2019

DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing

We propose a differentiable sphere tracing algorithm to bridge the gap b...
research
06/30/2023

MARF: The Medial Atom Ray Field Object Representation

We propose Medial Atom Ray Fields (MARFs), a novel neural object represe...
research
02/05/2022

Spelunking the Deep: Guaranteed Queries on General Neural Implicit Surfaces via Range Analysis

Neural implicit representations, which encode a surface as the level set...
research
08/07/2023

Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surface

This paper proposes a technique for efficiently modeling dynamic humans ...
research
01/22/2022

MIP-plicits: Level of Detail Factorization of Neural Implicits Sphere Tracing

We introduce MIP-plicits, a novel approach for rendering 3D and 4D Neura...
research
05/02/2022

Physics-Based Inverse Rendering using Combined Implicit and Explicit Geometries

Mathematically representing the shape of an object is a key ingredient f...
research
06/07/2021

Deep Medial Fields

Implicit representations of geometry, such as occupancy fields or signed...

Please sign up or login with your details

Forgot password? Click here to reset