collaborators

22 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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-…

cs.LG2026

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.…

cs.LG2026

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…

cs.GR2026

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.…