6 papers
Autonomous Discovery of Wireless Communications Algorithms
Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer +4
Large language model (LLM)-driven evolutionary search is an emerging algorithm-discovery paradigm that has already produced novel results in several scientific fields. Yet its appl…
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Jorge Condor, Nicolas Moenne-Loccoz, Merlin Nimier-David +3
Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields…
Stochastic Preconditioning for Neural Field Optimization
Selena Ling, Merlin Nimier-David, Alec Jacobson +1
Neural fields are a highly effective representation across visual computing. This work observes that fitting these fields is greatly improved by incorporating spatial stochasticity…
Radiance Surfaces: Optimizing Surface Representations with a 5D Radiance Field Loss
Ziyi Zhang, Nicolas Roussel, Thomas Müller +4
We present a fast and simple technique to convert images into a radiance surface-based scene representation. Building on existing radiance volume reconstruction algorithms, we intr…
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Xuanchi Ren, Tianchang Shen, Jiahui Huang +7
We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage…
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…