How Far Can We Compress Instant-NGP-Based NeRF?
Abstract In recent years Neural Radiance Field (NeRF) has demonstrated remarkable
capabilities in representing 3D scenes. To expedite the rendering process learnable explicit …
capabilities in representing 3D scenes. To expedite the rendering process learnable explicit …
Citygen: Infinite and controllable 3d city layout generation
City layout generation has recently gained significant attention. The goal of this task is to
automatically generate the layout of a city scene, including elements such as roads …
automatically generate the layout of a city scene, including elements such as roads …
Octree-gs: Towards consistent real-time rendering with lod-structured 3d gaussians
The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and
efficiency compared to NeRF-based neural scene representations. While demonstrating the …
efficiency compared to NeRF-based neural scene representations. While demonstrating the …
GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
While recent advances in neural radiance field enable realistic digitization for large-scale
scenes the image-capturing process is still time-consuming and labor-intensive. Previous …
scenes the image-capturing process is still time-consuming and labor-intensive. Previous …
PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios
We address the challenge of content diversity and controllability in pedestrian simulation for
driving scenarios. Recent pedestrian animation frameworks have a significant limitation …
driving scenarios. Recent pedestrian animation frameworks have a significant limitation …
Citygaussian: Real-time high-quality large-scale scene rendering with gaussians
The advancement of real-time 3D scene reconstruction and novel view synthesis has been
significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large …
significantly propelled by 3D Gaussian Splatting (3DGS). However, effectively training large …
Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery
We present a neural radiance field method for urban-scale semantic and building-level
instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a …
instance segmentation from aerial images by lifting noisy 2D labels to 3D. This is a …
XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
G Wang, J Zhang, F Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
We propose XScale-NVS for high-fidelity cross-scale novel view synthesis of real-world
large-scale scenes. Existing representations based on explicit surface suffer from …
large-scale scenes. Existing representations based on explicit surface suffer from …
Scenex: Procedural controllable large-scale scene generation via large-language models
Due to its great application potential, large-scale scene generation has drawn extensive
attention in academia and industry. Recent research employs powerful generative models to …
attention in academia and industry. Recent research employs powerful generative models to …
City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Web
K Song, J Zhang - arXiv preprint arXiv:2312.16457, 2023 - arxiv.org
NeRF has significantly advanced 3D scene reconstruction, capturing intricate details across
various environments. Existing methods have successfully leveraged radiance field baking …
various environments. Existing methods have successfully leveraged radiance field baking …