35 citations · 56 across the 15 of their papers we have counts for
21 papers
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
Shuhong Zheng, Michael Oechsle, Erik Sandström +3
Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. Howe…
HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild
Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno +2
Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively h…
Learning Neural Exposure Fields for View Synthesis
Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona +5
Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchma…
AnyUp: Universal Feature Upsampling
Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona +4
We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsample…
Masks make discriminative models great again!
Tianshi Cao, Marie-Julie Rakotosaona, Ben Poole +2
We present Image2GS, a novel approach that addresses the challenging problem of reconstructing photorealistic 3D scenes from a single image by focusing specifically on the image-to…
LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering
Jonas Kulhanek, Marie-Julie Rakotosaona, Fabian Manhardt +5
In this work, we present a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. Our ap…
Text To 3D Object Generation For Scalable Room Assembly
Sonia Laguna, Alberto Garcia-Garcia, Marie-Julie Rakotosaona +3
Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenario…
P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising
Mathias Vogel, Keisuke Tateno, Marc Pollefeys +3
In this work, we tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schrödinger bridges to points clouds. Unlike previous approaches that pred…
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS
Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona +7
Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-t…
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
Fangjinhua Wang, Marie-Julie Rakotosaona, Michael Niemeyer +3
Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images. However, reconstructing real-world captures of complex scenes still remains a chall…
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
Yichen Xie, Chenfeng Xu, Marie-Julie Rakotosaona +5
By identifying four important components of existing LiDAR-camera 3D object detection methods (LiDAR and camera candidates, transformation, and fusion outputs), we observe that all…
NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes
Marie-Julie Rakotosaona, Fabian Manhardt, Diego Martin Arroyo +3
With the introduction of Neural Radiance Fields (NeRFs), novel view synthesis has recently made a big leap forward. At the core, NeRF proposes that each 3D point can emit radiance,…
SPARF: Neural Radiance Fields from Sparse and Noisy Poses
Prune Truong, Marie-Julie Rakotosaona, Fabian Manhardt +1
Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance, it relies on the avai…
Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion
Dario Pavllo, David Joseph Tan, Marie-Julie Rakotosaona +1
Neural Radiance Fields (NeRF) coupled with GANs represent a promising direction in the area of 3D reconstruction from a single view, owing to their ability to efficiently model arb…
Differentiable Surface Triangulation
Marie-Julie Rakotosaona, Noam Aigerman, Niloy Mitra +2
Triangle meshes remain the most popular data representation for surface geometry. This ubiquitous representation is essentially a hybrid one that decouples continuous vertex locati…
Learning Delaunay Surface Elements for Mesh Reconstruction
Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman +2
We present a method for reconstructing triangle meshes from point clouds. Existing learning-based methods for mesh reconstruction mostly generate triangles individually, making it…
Correspondence Learning via Linearly-invariant Embedding
Riccardo Marin, Marie-Julie Rakotosaona, Simone Melzi +1
In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. The proposed pipeline is an extension and a general…
Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation
Marie-Julie Rakotosaona, Maks Ovsjanikov
We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our…
Effective Rotation-invariant Point CNN with Spherical Harmonics kernels
Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty +1
We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-bas…
OperatorNet: Recovering 3D Shapes From Difference Operators
Ruqi Huang, Marie-Julie Rakotosaona, Panos Achlioptas +2
This paper proposes a learning-based framework for reconstructing 3D shapes from functional operators, compactly encoded as small-sized matrices. To this end we introduce a novel n…
PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
Marie-Julie Rakotosaona, Vittorio La Barbera, Paul Guerrero +2
Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point…