190 citations · 998 across the 71 of their papers we have counts for
85 papers
Learnable Spectral Activations
Tamir Shor, Or Litany, Alex Bronstein
Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods improve fitting primarily by…
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
Merav Keidar, Tomer Borreda, Rajalakshmi Nandakumar +1
Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observations beyond the original traje…
WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis
Michael Green, Gavriel Habib, Dvir Samuel +4
Projection-conditioned novel view synthesis (NVS) warps an explicit 3D reconstruction of the input view into the target camera and conditions a generator on the warped rendering. T…
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows
Daniel Gilo, Sven Elflein, Ido Sobol +1
Conditional diffusion and flow models routinely fail to satisfy the very constraints that define their task. For instance, a depth-conditioned model often produces images whose re-…
VideoMDM: Towards 3D Human Motion Generation From 2D Supervision
Amir Mann, Gal Michael Harari, Merav Keidar +1
We introduce VideoMDM, a diffusion-based framework that trains 3D human motion priors directly from accurate 2D poses extracted from monocular videos, without any 3D ground truth.…
Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning
Ido Sobol, Kihyuk Sohn, Yoav Blum +4
We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-…
Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions
Etai Sella, Hao Phung, Nitay Amiel +3
Text-based 2D image editing models have recently reached an impressive level of maturity, motivating a growing body of work that heavily depends on these models to drive 3D edits.…
SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes
Léopold Maillard, Francis Engelmann, Tom Durand +5
Indoor 3D scenes are ultimately meant to be used: an embodied agent should be able to navigate, reach objects, and complete diverse activities. Yet whether a given scene actually s…
Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization
Matan Levy, Gavriel Habib, Issar Tzachor +5
Template-free animatable head avatars can achieve high visual fidelity by learning expression-dependent facial deformation directly from a subject's capture, avoiding parametric fa…
DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer
Yuxuan Zhang, Katarína Tóthová, Zian Wang +7
Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as a promising solution as it enable…
SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervision
Avigail Cohen Rimon, Amir Mann, Mirela Ben Chen +1
3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveragin…
Test-Time Training with KV Binding Is Secretly Linear Attention
Junchen Liu, Sven Elflein, Or Litany +2
Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. Howev…
RadarGen: Automotive Radar Point Cloud Generation from Cameras
Tomer Borreda, Fangqiang Ding, Sanja Fidler +2
We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to…
SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling
Elisabetta Fedele, Francis Engelmann, Ian Huang +3
Generative methods for 3D assets have recently achieved remarkable progress, yet providing intuitive and precise control over the object geometry remains a key challenge. Existing…
InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization
Daniel Gilo, Or Litany
We address the task of multi-view image editing from sparse input views, where the inputs can be seen as a mix of images capturing the scene from different viewpoints. The goal is…
Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video
Yarin Bekor, Gal Michael Harari, Or Perel +1
We present Gaussian See, Gaussian Do, a novel approach for semantic 3D motion transfer from multiview video. Our method enables rig-free, cross-category motion transfer between obj…
Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis
Saar Stern, Ido Sobol, Or Litany
The goal of Novel View Synthesis (NVS) is to generate realistic images of a given content from unseen viewpoints. But how can we trust that a generated image truly reflects the int…
Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising
Assaf Singer, Noam Rotstein, Amir Mann +2
Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control. Prior methods for motion-condit…
MonSTeR: a Unified Model for Motion, Scene, Text Retrieval
Luca Collorone, Matteo Gioia, Massimiliano Pappa +5
Intention drives human movement in complex environments, but such movement can only happen if the surrounding context supports it. Despite the intuitive nature of this mechanism, e…
FRIDU: Functional Map Refinement with Guided Image Diffusion
Avigail Cohen Rimon, Mirela Ben-Chen, Or Litany
We propose a novel approach for refining a given correspondence map between two shapes. A correspondence map represented as a functional map, namely a change of basis matrix, can b…
ZDySS -- Zero-Shot Dynamic Scene Stylization using Gaussian Splatting
Abhishek Saroha, Florian Hofherr, Mariia Gladkova +3
Stylizing a dynamic scene based on an exemplar image is critical for various real-world applications, including gaming, filmmaking, and augmented and virtual reality. However, achi…
ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment
Tomer Borreda, Daniel Freedman, Or Litany
We present ReHub, a novel graph transformer architecture that achieves linear complexity through an efficient reassignment technique between nodes and virtual nodes. Graph transfor…
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
Chensheng Peng, Ido Sobol, Masayoshi Tomizuka +3
We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the…
Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar Consistency Conditions
Daniel Gilo, Tzofi Klinghoffer, Or Litany
Neural field methods, initially successful in the inverse rendering domain, have recently been extended to CT reconstruction, marking a paradigm shift from traditional techniques.…