81 citations · 171 across the 20 of their papers we have counts for
7 papers · 1 filter
Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion
Kira Prabhu, Jane Wu, Lynn Tsai +4
This paper presents a novel approach to inpainting 3D regions of a scene, given masked multi-view images, by distilling a 2D diffusion model into a learned 3D scene representation…
SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration
Daniel Duckworth, Peter Hedman, Christian Reiser +5
Recent techniques for real-time view synthesis have rapidly advanced in fidelity and speed, and modern methods are capable of rendering near-photorealistic scenes at interactive fr…
Eclipse: Disambiguating Illumination and Materials using Unintended Shadows
Dor Verbin, Ben Mildenhall, Peter Hedman +3
Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This pr…
Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Jonathan T. Barron, Ben Mildenhall, Dor Verbin +2
Neural Radiance Field training can be accelerated through the use of grid-based representations in NeRF's learned mapping from spatial coordinates to colors and volumetric density.…
Vox-E: Text-guided Voxel Editing of 3D Objects
Etai Sella, Gal Fiebelman, Peter Hedman +1
Large scale text-guided diffusion models have garnered significant attention due to their ability to synthesize diverse images that convey complex visual concepts. This generative…
MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
Christian Reiser, Richard Szeliski, Dor Verbin +5
Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time render…
BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis
Lior Yariv, Peter Hedman, Christian Reiser +5
We present a method for reconstructing high-quality meshes of large unbounded real-world scenes suitable for photorealistic novel view synthesis. We first optimize a hybrid neural…