20 citations · 57 across the 7 of their papers we have counts for
7 papers
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht +4
Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somew…
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai +5
Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However, it may require a large number of Gaussians, which creates a substant…
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation
Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht +1
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and…
: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi
Reconstructing the 3D shape of an object from a single RGB image is a long-standing and highly challenging problem in computer vision. In this paper, we propose a novel method for…
RealFusion: 360° Reconstruction of Any Object from a Single Image
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina +1
We consider the problem of reconstructing a full 360° photographic model of an object from a single image of it. We do so by fitting a neural radiance field to the image, but find…
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina +1
Unsupervised localization and segmentation are long-standing computer vision challenges that involve decomposing an image into semantically-meaningful segments without any labeled…