We present MetricTrail, a streaming system for accurate camera motion estimation and dense reconstruction from long monocular videos. To keep inference efficient over long sequences, we revisit DPVO's sparse local estimator. We find that single-image metric depth substantially improves its trajectory accuracy, without...
Jing-Nan Gao, Jia-Hui Huang, Sven Elflein et al.· 0 citations
LucidLyra is a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents, and enables downstream applications including 3D scene editing, 3D asset mining, and robotic simulation.
Oliver Hahn, R. Marcuzzi, Sangeetha Grama Srinivasan et al.· 0 citations
We introduce Foundation4D, a unified feed-forward model for geometry estimation, 3D detection, semantic occupancy, and Gaussian reconstruction from multi-camera driving video. A shared backbone uses factorized spatiotemporal attention to efficiently combine observations across cameras and time. Our video inference pipe...
Nvidia Sérgio Agostinho, Maximilian Apodaca, Emmanuel Attia et al.· 0 citations
Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with established vision-language pretraining pipelines. Recent advances in pixel-space modeling offer an encoder-free alternative, but extending...
UniD is introduced, a unified video model that jointly predicts eight dense scene properties-depth, surface normals, semantic segmentation, boundaries, human parts, albedo, shading, and materials-all learned from disjoint, domain-specific datasets.