260 citations · 321 across the 45 of their papers we have counts for
57 papers · 1 filter
Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction
Ziren Gong, Guo Chen, Yongjia Li +13
4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations. Despite substantial progress in neural scene…
ProDyGS: Dynamic Gaussian Splatting from a Single Static Monocular Camera
Ugo Leone Cavalcanti, Fabio Tosi, Matteo Poggi +4
We present ProDyGS, a novel dynamic 3D Gaussian Splatting framework for high-quality novel view synthesis from videos captured by a single static camera. While existing methods rel…
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Igor Pavlovic, Thiemo Wandel, Anton Obukhov +6
Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computational photography, and robotics,…
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
Ziren Gong, Xiaohan Li, Fabio Tosi +4
This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on…
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
Fabio Tosi, Luca Bartolomei, Matteo Poggi +1
Monocular depth estimation has seen remarkable progress through foundation models achieving robust zero-shot generalization, yet their computational demands place them far beyond t…
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
Ninghui Xu, Fabio Tosi, Lihui Wang +5
Conventional frame-based cameras capture rich contextual information but suffer from limited temporal resolution and motion blur in dynamic scenes. Event cameras offer an alternati…
EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors
Luca Bartolomei, Fabio Tosi, Matteo Poggi +2
We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images…
FlowIt: Global Matching via Hierarchical Transformers and Optimal Transport for Optical Flow
Sadra Safadoust, Fabio Tosi, Matteo Poggi +1
We present FlowIt, a novel architecture for optical flow estimation that combines global matching with confidence and occlusion-guided refinement. At its core, FlowIt leverages a h…
FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM
Yuchen Wu, Jiahe Li, Fabio Tosi +3
We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches for accurate and robus…
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
Tjark Behrens, Anton Obukhov, Bingxin Ke +3
We introduce StereoSpace, a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning, without explicit depth or warpin…
Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation
Luca Bartolomei, Enrico Mannocci, Fabio Tosi +2
Event cameras capture sparse, high-temporal-resolution visual information, making them particularly suitable for challenging environments with high-speed motion and strongly varyin…
FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
Matteo Poggi, Fabio Tosi
We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow…
Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videos
Ziren Gong, Xiaohan Li, Fabio Tosi +4
We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The system features two key components: CL…
DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations
Ziren Gong, Xiaohan Li, Fabio Tosi +4
This paper presents DINO-SLAM, a DINO-informed design strategy to enhance implicit (Neural Radiance Field -- NeRF) and explicit representations (Gaussian Splatting -- GS) in SLAM s…
WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields
Sadra Safadoust, Fabio Tosi, Fatma Güney +1
We introduce WarpRF, a training-free general-purpose framework for quantifying the uncertainty of radiance fields. Built upon the assumption that photometric and geometric consiste…
NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
Pierluigi Zama Ramirez, Fabio Tosi, Luigi Di Stefano +36
This paper reports on the NTIRE 2025 challenge on HR Depth From images of Specular and Transparent surfaces, held in conjunction with the New Trends in Image Restoration and Enhanc…
The Fourth Monocular Depth Estimation Challenge
Anton Obukhov, Matteo Poggi, Fabio Tosi +54
This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a…
HS-SLAM: Hybrid Representation with Structural Supervision for Improved Dense SLAM
Ziren Gong, Fabio Tosi, Youmin Zhang +2
NeRF-based SLAM has recently achieved promising results in tracking and reconstruction. However, existing methods face challenges in providing sufficient scene representation, capt…
Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail
Luca Bartolomei, Fabio Tosi, Matteo Poggi +1
We introduce Stereo Anywhere, a novel stereo-matching framework that combines geometric constraints with robust priors from monocular depth Vision Foundation Models (VFMs). By eleg…
Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairs
Sadra Safadoust, Fabio Tosi, Fatma Güney +1
3D Gaussian Splatting (GS) significantly struggles to accurately represent the underlying 3D scene geometry, resulting in inaccuracies and floating artifacts when rendering depth m…
Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
Fabio Tosi, Pierluigi Zama Ramirez, Matteo Poggi
We present a novel approach designed to address the complexities posed by challenging, out-of-distribution data in the single-image depth estimation task. Starting with images that…
A Survey on Deep Stereo Matching in the Twenties
Fabio Tosi, Luca Bartolomei, Matteo Poggi
Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning. While previous surveys in the late 2010s…
Active Stereo in the Wild through Virtual Pattern Projection
Luca Bartolomei, Matteo Poggi, Fabio Tosi +2
This paper presents a novel general-purpose guided stereo paradigm that mimics the active stereo principle by replacing the unreliable physical pattern projector with a depth senso…
Federated Online Adaptation for Deep Stereo
Matteo Poggi, Fabio Tosi
We introduce a novel approach for adapting deep stereo networks in a collaborative manner. By building over principles of federated learning, we develop a distributed framework all…