Instruct-nerf2nerf: Editing 3d scenes with instructions
We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a
scene and the collection of images used to reconstruct it, our method uses an image …
scene and the collection of images used to reconstruct it, our method uses an image …
Lerf: Language embedded radiance fields
Humans describe the physical world using natural language to refer to specific 3D locations
based on a vast range of properties: visual appearance, semantics, abstract associations, or …
based on a vast range of properties: visual appearance, semantics, abstract associations, or …
Scannet++: A high-fidelity dataset of 3d indoor scenes
We present ScanNet++, a large-scale dataset that couples together capture of high-quality
and commodity-level geometry and color of indoor scenes. Each scene is captured with a …
and commodity-level geometry and color of indoor scenes. Each scene is captured with a …
Suds: Scalable urban dynamic scenes
We extend neural radiance fields (NeRFs) to dynamic large-scale urban scenes. Prior work
tends to reconstruct single video clips of short durations (up to 10 seconds). Two reasons …
tends to reconstruct single video clips of short durations (up to 10 seconds). Two reasons …
Nerfacc: Efficient sampling accelerates nerfs
Abstract Optimizing and rendering Neural Radiance Fields is computationally expensive
due to the vast number of samples required by volume rendering. Recent works have …
due to the vast number of samples required by volume rendering. Recent works have …
Physgaussian: Physics-integrated 3d gaussians for generative dynamics
We introduce PhysGaussian a new method that seamlessly integrates physically grounded
Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis …
Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis …
Matrixcity: A large-scale city dataset for city-scale neural rendering and beyond
Neural radiance fields (NeRF) and its subsequent variants have led to remarkable progress
in neural rendering. While most of recent neural rendering works focus on objects and small …
in neural rendering. While most of recent neural rendering works focus on objects and small …
Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
Abstract Neural Radiance Fields (NeRFs) have shown promise in applications like view
synthesis and depth estimation but learning from multiview images faces inherent …
synthesis and depth estimation but learning from multiview images faces inherent …
Nerfbusters: Removing ghostly artifacts from casually captured nerfs
Abstract Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as
floaters or flawed geometry when rendered outside the input camera trajectory. Existing …
floaters or flawed geometry when rendered outside the input camera trajectory. Existing …
Nersemble: Multi-view radiance field reconstruction of human heads
We focus on reconstructing high-fidelity radiance fields of human heads, capturing their
animations over time, and synthesizing re-renderings from novel viewpoints at arbitrary time …
animations over time, and synthesizing re-renderings from novel viewpoints at arbitrary time …