Florian Barthel
YOU?
Author Swipe
View article: 3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods
3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods Open
3D Gaussian Splatting (3DGS) has emerged as a cutting‐edge technique for real‐time radiance field rendering, offering state‐of‐the‐art performance in terms of both quality and speed. 3DGS models a scene as a collection of three‐dimensional…
View article: Improving Adaptive Density Control for 3D Gaussian Splatting
Improving Adaptive Density Control for 3D Gaussian Splatting Open
610
View article: 3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods
3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods Open
3D Gaussian Splatting (3DGS) has emerged as a cutting-edge technique for real-time radiance field rendering, offering state-of-the-art performance in terms of both quality and speed. 3DGS models a scene as a collection of three-dimensional…
View article: Creating Sorted Grid Layouts with Gradient-based Optimization
Creating Sorted Grid Layouts with Gradient-based Optimization Open
Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationships. This approach facilitates the effective sorting of diver…
View article: Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks
Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks Open
NeRF-based 3D-aware Generative Adversarial Networks (GANs) like EG3D or GIRAFFE have shown very high rendering quality under large representational variety. However, rendering with Neural Radiance Fields poses challenges for 3D application…
View article: Multi-View Inversion for 3D-aware Generative Adversarial Networks
Multi-View Inversion for 3D-aware Generative Adversarial Networks Open
194
View article: Compact 3D Scene Representation via Self-Organizing Gaussian Grids
Compact 3D Scene Representation via Self-Organizing Gaussian Grids Open
3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at high-quality. Howev…
View article: Multi-view Inversion for 3D-aware Generative Adversarial Networks
Multi-view Inversion for 3D-aware Generative Adversarial Networks Open
Current 3D GAN inversion methods for human heads typically use only one single frontal image to reconstruct the whole 3D head model. This leaves out meaningful information when multi-view data or dynamic videos are available. Our method bu…
View article: Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes
Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes Open
Current scene graph datasets suffer from strong long-tail distributions of their predicate classes. Due to a very low number of some predicate classes in the test sets, no reliable metrics can be retrieved for the rarest classes. We constr…
View article: Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes
Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes Open
Current scene graph datasets suffer from strong long-tail distributions of their predicate classes. Due to a very low number of some predicate classes in the test sets, no reliable metrics can be retrieved for the rarest classes. We constr…
View article: Controlling 3D Objects in 2D Image Synthesis
Controlling 3D Objects in 2D Image Synthesis Open
In this work, we propose a method that enforces explicit control over various attributes during the image generation process in a generative adversarial net. We propose a semi-supervised learning procedure that allows us to use a quantized…