We present ZeroRF a novel per-scene optimization method addressing the challenge of
sparse view 360deg reconstruction in neural field representations. Current breakthroughs …

We present ZeroRF, a novel per-scene optimization method addressing the challenge of
sparse view 360° reconstruction in neural field representations. Current breakthroughs like …

We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality
mesh from merely four input images in less than one second. Different from previous large …

Abstract Neural Radiance Fields (NeRF) have significantly advanced the generation of
highly realistic and expressive 3D scenes. However, the task of editing NeRF, particularly in …

We propose a novel approach for 3D mesh reconstruction from multi-view images. Our
method takes inspiration from large reconstruction models like LRM that use a transformer …

Neural Radiance Fields (NeRF) has demonstrated its ability to generate high-quality
synthesized views. Nonetheless, due to its slow inference speed, there is a need to explore …

We present a differentiable representation, DMesh, for general 3D triangular meshes.
DMesh considers both the geometry and connectivity information of a mesh. In our design …

Recent probabilistic methods for 3D triangular meshes capture diverse shapes by
differentiable mesh connectivity, but face high computational costs with increased shape …

Inferring 3D structures from sparse, unposed observations is challenging due to its
unconstrained nature. Recent methods propose to predict implicit representations directly …

Accurately reconstructing a 3D scene including explicit geometry information is both
attractive and challenging. Geometry reconstruction can benefit from incorporating …