8 papers · 1 filter
MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction
Jingnan Gao, Jiahui Huang, Sven Elflein +8
We present MetricTrail, a streaming system for accurate camera motion estimation and dense reconstruction from long monocular videos. To keep inference efficient over long sequence…
LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation
Oliver Hahn, Rodrigo Marcuzzi, Sangeetha Grama Srinivasan +7
We present LucidLyra, a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents. While…
Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
Henry Che, Xuanchi Ren, Sanja Fidler +3
We present LidarVerse, a real-time unified LiDAR world model for sensor simulation across tasks and sensors. Existing LiDAR simulators largely follow one of two complementary parad…
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
Cong Wei, Xuanchi Ren, Bryan Chu +8
Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with…
Addressable Memory for Video World Models
Xindi Wu, Sven Elflein, James Lucas +5
We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames.…
VGG-T: Offline Feed-Forward 3D Reconstruction at Scale
Sven Elflein, Ruilong Li, Sérgio Agostinho +4
We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requirements grow quadratically w…
Depth Completion as Parameter-Efficient Test-Time Adaptation
Bingxin Ke, Qunjie Zhou, Jiahui Huang +5
We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unli…
Motion Attribution for Video Generation
Xindi Wu, Despoina Paschalidou, Jun Gao +5
Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a m…