49 citations · 230 across the 30 of their papers we have counts for
46 papers
Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
Yung-Hsu Yang, Luigi Piccinelli, Samuel Rota Bulò +7
Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors, trading away cost, power, and integration simplicity. This mot…
DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objects
Narek Tumanyan, Samuel Rota Bulò, Denis Rozumny +5
Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous approaches have attempted to overcome the ill-posedness of the task by distilling prio…
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Nikhil Keetha, Norman Müller, Johannes Schönberger +14
We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, dept…
FlowR: Flowing from Sparse to Dense 3D Reconstructions
Tobias Fischer, Samuel Rota Bulò, Yung-Hsu Yang +7
3D Gaussian splatting enables high-quality novel view synthesis (NVS) at real-time frame rates. However, its quality drops sharply as we depart from the training views. Thus, dense…
A Recipe for Generating 3D Worlds From a Single Image
Katja Schwarz, Denys Rozumnyi, Samuel Rota Bulò +2
We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires…
Hardware-Rasterized Ray-Based Gaussian Splatting
Samuel Rota Bulò, Nemanja Bartolovic, Lorenzo Porzi +1
We present a novel, hardware rasterized rendering approach for ray-based 3D Gaussian Splatting (RayGS), obtaining both fast and high-quality results for novel view synthesis. Our w…
Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes
Stefano Esposito, Anpei Chen, Christian Reiser +7
High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy ge…
MultiDiff: Consistent Novel View Synthesis from a Single Image
Norman Müller, Katja Schwarz, Barbara Roessle +4
We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image i…
ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing
Jun-Kun Chen, Samuel Rota Bulò, Norman Müller +3
This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene edi…
Dynamic 3D Gaussian Fields for Urban Areas
Tobias Fischer, Jonas Kulhanek, Samuel Rota Bulò +3
We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. Existing works are not well suited for applications like…
Revising Densification in Gaussian Splatting
Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder
In this paper, we address the limitations of Adaptive Density Control (ADC) in 3D Gaussian Splatting (3DGS), a scene representation method achieving high-quality, photorealistic re…
Robust Gaussian Splatting
François Darmon, Lorenzo Porzi, Samuel Rota-Bulò +1
In this paper, we address common error sources for 3D Gaussian Splatting (3DGS) including blur, imperfect camera poses, and color inconsistencies, with the goal of improving its ro…
Multi-Level Neural Scene Graphs for Dynamic Urban Environments
Tobias Fischer, Lorenzo Porzi, Samuel Rota Bulò +2
We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restrict…
HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
Haithem Turki, Vasu Agrawal, Samuel Rota Bulò +5
Neural radiance fields provide state-of-the-art view synthesis quality but tend to be slow to render. One reason is that they make use of volume rendering, thus requiring many samp…
VR-NeRF: High-Fidelity Virtualized Walkable Spaces
Linning Xu, Vasu Agrawal, William Laney +10
We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields. To…
GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
Barbara Roessle, Norman Müller, Lorenzo Porzi +3
Neural Radiance Fields (NeRF) have shown impressive novel view synthesis results; nonetheless, even thorough recordings yield imperfections in reconstructions, for instance due to…
OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
Paul-Edouard Sarlin, Daniel DeTone, Tsun-Yi Yang +7
Humans can orient themselves in their 3D environments using simple 2D maps. Differently, algorithms for visual localization mostly rely on complex 3D point clouds that are expensiv…
Panoptic Lifting for 3D Scene Understanding with Neural Fields
Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Buló +4
We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images…
DiffRF: Rendering-Guided 3D Radiance Field Diffusion
Norman Müller, Yawar Siddiqui, Lorenzo Porzi +3
We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, l…
AutoRF: Learning 3D Object Radiance Fields from Single View Observations
Norman Müller, Andrea Simonelli, Lorenzo Porzi +3
We introduce AutoRF - a new approach for learning neural 3D object representations where each object in the training set is observed by only a single view. This setting is in stark…
Dense Prediction with Attentive Feature Aggregation
Yung-Hsu Yang, Thomas E. Huang, Min Sun +3
Aggregating information from features across different layers is an essential operation for dense prediction models. Despite its limited expressiveness, feature concatenation domin…
Inferring Latent Domains for Unsupervised Deep Domain Adaptation
Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò +2
Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data…
Weakly Supervised Multi-Object Tracking and Segmentation
Idoia Ruiz, Lorenzo Porzi, Samuel Rota Bulò +2
We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do n…
Improving Panoptic Segmentation at All Scales
Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder
Crop-based training strategies decouple training resolution from GPU memory consumption, allowing the use of large-capacity panoptic segmentation networks on multi-megapixel images…