29 citations · 58 across the 29 of their papers we have counts for
34 papers
SplashSplat: Reconstructing Splashing Liquids from Real-World Multi-View Videos
Peiyu Liu, Dingxi Zhang, Federico Tombari +3
A splash lives for a fraction of a second: sheets tear into ligaments and droplets, appearance is view-dependent and nearly textureless, and little persists long enough to track. R…
GenRec: Knowing Where to Reconstruct and Where to Generate
Ata Çelen, Jaewoo Jung, Federico Tombari +4
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated on…
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
Haofei Xu, Rundi Wu, Philipp Henzler +7
State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage…
OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention
Kunyi Li, Michael Niemeyer, Sen Wang +3
Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view…
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
Felix Wimbauer, Fabian Manhardt, Michael Oechsle +4
The synthesis of immersive 3D scenes from text is rapidly maturing, driven by novel video generative models and feed-forward 3D reconstruction, with vast potential in AR/VR and wor…
Unified Semantic Transformer for 3D Scene Understanding
Sebastian Koch, Johanna Wald, Hidenobu Matsuki +3
Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly be…
SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation
Peter Siegel, Federico Tombari, Marc Pollefeys +1
We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constru…
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…
OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
Atakan Topaloglu, Kunyi Li, Michael Niemeyer +3
Sparse-view novel view synthesis is fundamentally ill-posed due to severe geometric ambiguity. Current methods are caught in a trade-off: regressive models are geometrically faithf…
CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis
Xin Kong, Daniel Watson, Yannick Strümpler +2
Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in worl…
3D-LATTE: Latent Space 3D Editing from Textual Instructions
Maria Parelli, Michael Oechsle, Michael Niemeyer +2
Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality…
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…
Video Perception Models for 3D Scene Synthesis
Rui Huang, Guangyao Zhai, Zuria Bauer +5
Traditionally, 3D scene synthesis requires expert knowledge and significant manual effort. Automating this process could greatly benefit fields such as architectural design, roboti…
Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
Gaia Di Lorenzo, Federico Tombari, Marc Pollefeys +1
Learning effective multi-modal 3D representations of objects is essential for numerous applications, such as augmented reality and robotics. Existing methods often rely on task-spe…
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…
SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
Haoliang Shang, Hanyu Wu, Guangyao Zhai +4
Scene graphs capture complex relationships among objects, serving as strong priors for content generation and manipulation. Yet, reasonably manipulating scene graphs -- whether by…
RelationField: Relate Anything in Radiance Fields
Sebastian Koch, Johanna Wald, Mirco Colosi +4
Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from…
Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes
Thomas Wimmer, Michael Oechsle, Michael Niemeyer +1
State-of-the-art novel view synthesis methods achieve impressive results for multi-view captures of static 3D scenes. However, the reconstructed scenes still lack "liveliness," a k…
Search3D: Hierarchical Open-Vocabulary 3D Segmentation
Ayca Takmaz, Alexandros Delitzas, Robert W. Sumner +3
Open-vocabulary 3D segmentation enables exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance segmentation primarily focus on…
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…
Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians
Erik Sandström, Keisuke Tateno, Michael Oechsle +4
3D Gaussian Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous Localization and Mapping (SLAM), as it provides a compact…
OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
Francis Engelmann, Fabian Manhardt, Michael Niemeyer +3
Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the tradition…
SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs
Yang Miao, Francis Engelmann, Olga Vysotska +3
We introduce a novel problem, i.e., the localization of an input image within a multi-modal reference map represented by a database of 3D scene graphs. These graphs comprise multip…
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
Francis Engelmann, Ayca Takmaz, Jonas Schult +25
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this wo…