190 citations · 595 across the 39 of their papers we have counts for
7 papers · 1 filter
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
Qi Wu, Janick Martinez Esturo, Ashkan Mirzaei +2
3D Gaussian Splatting (3DGS) enables efficient reconstruction and high-fidelity real-time rendering of complex scenes on consumer hardware. However, due to its rasterization-based…
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Hanxue Liang, Jiawei Ren, Ashkan Mirzaei +8
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis. However, these models often struggle wi…
Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Ruofan Liang, Zan Gojcic, Merlin Nimier-David +4
The correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formatio…
3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
Nicolas Moenne-Loccoz, Ashkan Mirzaei, Or Perel +6
Particle-based representations of radiance fields such as 3D Gaussian Splatting have found great success for reconstructing and re-rendering of complex scenes. Most existing method…
Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
Dongsu Zhang, Francis Williams, Zan Gojcic +4
We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV). Contrary to prior work on AV scene completion, we…
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Yiming Li, Zehong Wang, Yue Wang +5
Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory. This selective retention is crucial for robotic perception,…
RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting
Ashkan Mirzaei, Riccardo De Lutio, Seung Wook Kim +5
Neural reconstruction approaches are rapidly emerging as the preferred representation for 3D scenes, but their limited editability is still posing a challenge. In this work, we pro…