In this paper we present a novel method for efficient and effective 3D surface reconstruction in open scenes.

Here we describe the method used to find the extrinsics and intrinsics defining the captured dataset. An overview of the method can be found in the Algorithm 1.

A neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly.

In practice, when training denoisers, we sample multiple noisy samples for each clean image and minimize the Mean Squared Error (MSE) loss for recovering the clean image.

In practice, when training denoisers, we sample multiple noisy samples for each clean image and minimize the Mean Squared Error (MSE) loss for recovering the clean image.

Codes are available at https://github.com/ZhangCYG/DDFHO.

We address the fundamental problem of learning implicit surfaces for shape inference without the need of 3D supervision.

We propose Scene Representation Networks (SRNs), a continuous, 3D-structure-aware scene representation that encodes both geometry and appearance. SRNs represent scenes as continuous functions that map world coordinates to a feature representation of local scene properties.