Neural radiance fields (NeRFs) refer to a suit of deep neural networks that are used to learn
and represent objects or scenes. Generally speaking, NeRFs have five main characters …

Neural surface reconstruction has been shown to be powerful for recovering dense 3D
surfaces via image-based neural rendering. However, current methods struggle to recover …

Abstract Recently 3D Gaussian Splatting has demonstrated impressive novel view synthesis
results reaching high fidelity and efficiency. However strong artifacts can be observed when …

3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction,
achieving high quality novel view synthesis and fast rendering speed. However, 3DGS fails …

Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera
intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain yet …

Abstract We present Stable Video 3D (SV3D)—a latent video diffusion model for high-
resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent …

Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV)
a reality. It requires one to generate safety critical scenarios beyond what can be collected …

Abstract Neural Radiance Field (NeRF) significantly degrades when only a limited number
of views are available. To complement the lack of 3D information, depth-based models, such …

Abstract 3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at
rendering photorealistic novel views of complex scenes. However recovering a high-quality …

We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D
meshes generation from a single unposed image in the wild using both2D and 3D priors. In …