Our world is full of identical objects (\emphe. g., cans of coke, cars of same model). These
duplicates, when seen together, provide additional and strong cues for us to effectively …

How to make inverse graphics/3D reconstruction more robust and work under more extreme
scenarios is a challenging and longstanding problem in computer vision. In this work, we …

Recent history has seen a tremendous growth of work exploring implicit representations of
geometry and radiance, popularized through Neural Radiance Fields (NeRF). Such works …

We are witnessing an explosion of neural implicit representations in computer vision and
graphics. Their applicability has recently expanded beyond tasks such as shape generation …

In this paper, we propose Flash3D, a method for scene reconstruction and novel view
synthesis from a single image which is both very generalisable and efficient. For …

3D neural rendering enables photo-realistic reconstruction of a specific scene by encoding
discontinuous inputs into a neural representation. Despite the remarkable rendering results …

We present 3DP3, a framework for inverse graphics that uses inference in a structured
generative model of objects, scenes, and images. 3DP3 uses (i) voxel models to represent …

A central challenge in 3D scene perception via inverse graphics is robustly modeling the
gap between 3D graphics and real-world data. We propose a novel 3D Neural Embedding …

Recently, neural implicit surfaces learning by volume rendering has become popular for
multi-view reconstruction. However, one key challenge remains: existing approaches lack …

We present a volume rendering-based neural surface reconstruction method that takes as
few as three disparate RGB images as input. Our key idea is to regularize the reconstruction …