Marc Pollefeys

Existing 3D asset generators can now produce objects that not only look good but also move and function realistically, passing physics tests for stability and collision-free articulation.

Fine-grained 3D object generation is now possible by directly controlling local geometry and appearance with text and shape primitives, bypassing the need for model retraining.

This work introduces a benchmark of 20 real scenes, from coherent streams to violent splashes, captured by seven synchronized, calibrated 4K cameras at 60 fps, with manually refined per-view liquid and container masks and fixed evaluation splits, and presents SplashSplat, built on a single principle: impose physical structure only where the observations can constrain it.

Decoupling ray geometry from scene distance breaks the pervasive pinhole bias of modern 3D vision, enabling a single model to recover metric point clouds zero-shot across standard, fisheye, and 360° cameras.

Achieving rich 3D structures without sacrificing runtime, this framework redefines the limits of Bundle Adjustment in computer vision.

LIME turns ordinary egocentric video into a powerful tool for robots to dynamically adjust their camera poses based on user intent, revolutionizing how we think about robotic perception.

Ditch the training wheels: OpenFrontier achieves strong zero-shot navigation by cleverly using visual-language models to identify semantic frontiers as subgoals.

Robots can now build 3D scene graphs that understand how objects move, enabling more robust manipulation of articulated objects in real-world environments.