9 papers
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
Jaewoo Jung, Hyeonseo Yu, Honggyu An +10
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effe…
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…
LangLoc: "Tell Me What You See"
Shaurya Kishore Panwar, Roham Zendehdel Nobari, Shirley Feng Yi Lau +4
We tackle fine-grained indoor localization from natural language: given a free-form description of one's surroundings, estimate the observer's 2D position and heading within a know…
From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language Models
Bessie Dominguez-Dager, Francisco Gomez-Donoso, Miguel Cazorla +3
Action reasoning in egocentric video requires capturing fine-grained transitions of hand-object interactions, a task where general-purpose Vision-Language Models (VLMs) often strug…
ZipSplat: Fewer Gaussians, Better Splats
Alexander Veicht, Sunghwan Hong, Dániel Baráth +1
Feed-forward 3D Gaussian Splatting reconstructs scenes from images in seconds. Pixel-aligned methods keep every Gaussian grounded in an observation, but produce redundant, potentia…
Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys +1
Visual localization -- estimating a camera pose within a pre-existing map -- is a fundamental problem in computer vision. Floorplans are an attractive map representation: they are…
Gravity-aligned Rotation Averaging with Circular Regression
Linfei Pan, Marc Pollefeys, Dániel Baráth
Reconstructing a 3D scene from unordered images is pivotal in computer vision and robotics, with applications spanning crowd-sourced mapping and beyond. While global Structure-from…
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…