Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
This addresses the challenge of 3D reconstruction for computer vision applications where 3D data is scarce, offering a novel approach that avoids discretization issues of prior methods.
The paper tackles the problem of learning implicit 3D representations without requiring 3D supervision by proposing a differentiable rendering formulation that uses implicit differentiation to derive depth gradients, enabling training from RGB images. The result shows that single-view reconstructions rival those with full 3D supervision, and the method can produce watertight meshes for multi-view reconstruction.
Learning-based 3D reconstruction methods have shown impressive results. However, most methods require 3D supervision which is often hard to obtain for real-world datasets. Recently, several works have proposed differentiable rendering techniques to train reconstruction models from RGB images. Unfortunately, these approaches are currently restricted to voxel- and mesh-based representations, suffering from discretization or low resolution. In this work, we propose a differentiable rendering formulation for implicit shape and texture representations. Implicit representations have recently gained popularity as they represent shape and texture continuously. Our key insight is that depth gradients can be derived analytically using the concept of implicit differentiation. This allows us to learn implicit shape and texture representations directly from RGB images. We experimentally show that our single-view reconstructions rival those learned with full 3D supervision. Moreover, we find that our method can be used for multi-view 3D reconstruction, directly resulting in watertight meshes.