This paper presents TrainsBiolab, a real-world RGB-D dataset of cluttered transparent biomedical objects captured as calibrated multi-view sequences.

The paper proposes a novel method to improve the simultaneous representation of appearance and geometry in 3D Gaussian Splatting by introducing an additional geometry opacity parameter.

This paper investigates the transparency of DiffusionGemma, a model with a larger fraction of computation in a continuous latent space, and shows that it can be made more transparent by mapping inform…

This paper proposes methods for intrinsic decomposition of radiance fields using Gaussian splatting, enabling adaptive modeling, disentanglement, and editing of textures in images.

This paper identifies and explores a new type of physical adversarial attack on vision systems called Scratch-induced Lens Adversarial Streak Hijacking (SLASH), which causes persistent and selective o…

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…

The paper introduces a novel third-order, rotation-invariant spherical bispectrum for watermarking panoramic images, enabling reliable watermark embedding and extraction under arbitrary 3D rotations.

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

The paper introduces BilliardPhys-Bench, a new benchmark that demonstrates that current multimodal LLMs struggle with complex physical reasoning and predicting object dynamics in simulated environment…

The authors prove that two-dimensional ray tracing with thin lenses and plane mirrors using the ABCD model is Turing-complete.

This paper introduces Deformable Triangle Splatting, a method for representing non-convex shapes in radiance fields using triangles with learnable control points, enabling differentiable rendering.

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

The authors improve the bound on the chromatic number of t-perfect graphs from 199053 to 186 by refining the proof of Chudnovsky et al.

This paper introduces ComicJailbreak, a new benchmark demonstrating that structured visual narratives can effectively jailbreak Multimodal Large Language Models (MLLMs), requiring new safety alignment…

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

The paper proposes a visual program synthesis framework using a VLM to generate accurate training data for semiconductor inspection, mitigating the sim-to-real gap by applying input binarization to st…

This paper proposes a synthetic data generation framework to address the scarcity of real-world industrial defect images for training deep learning models in rotogravure printing quality control. The…

The paper proposes a fast and lightweight novel view synthesis method using a differentiable Multiplane Image (MPI) representation, achieving significant speed and size improvements over state-of-the-…