Modeling and re-rendering dynamic 3D scenes is a challenging task in 3D vision. Prior
approaches build on NeRF and rely on implicit representations. This is slow since it requires …

We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent
advances in neural rendering and probabilistic image generation. Existing approaches …

Abstract We introduce the Splatter Image an ultra-efficient approach for monocular 3D object
reconstruction. Splatter Image is based on Gaussian Splatting which allows fast and high …

We present a new approach termed GPS-Gaussian for synthesizing novel views of a
character in a real-time manner. The proposed method enables 2K-resolution rendering …

Although neural radiance fields (NeRF) have shown impressive advances in novel view
synthesis, most methods require multiple input images of the same scene with accurate …

Abstract Existing Human NeRF methods for reconstructing 3D humans typically rely on
multiple 2D images from multi-view cameras or monocular videos captured from fixed …

We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes.
Existing fast neural rendering methods generate realistic results, but primarily work for small …

We present a high-fidelity 3D generative adversarial network (GAN) inversion framework
that can synthesize photo-realistic novel views while preserving specific details of the input …

We present a one-shot method to infer and render a photorealistic 3D representation from a
single unposed image (eg, face portrait) in real-time. Given a single RGB input, our image …

Affordance grounding refers to the task of finding the area of an object with which one can
interact. It is a fundamental but challenging task as a successful solution requires the …