5 papers
FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors
Khiem Vuong, Deva Ramanan, Srinivasa Narasimhan
Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views ar…
Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videos
Anurag Ghosh, Francesco Pittaluga, Khiem Vuong +4
Self-driving simulations typically rely on data collected in a small number of cities or on hand-authored synthetic scenarios. Dashcam videos cover a far broader range of locations…
Novel View Synthesis as Video Completion
Qi Wu, Khiem Vuong, Minsik Jeon +2
We tackle the problem of sparse novel view synthesis (NVS) using video diffusion models; given () multi-view images of a scene and their camera poses, we predict the…
ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones
Anurag Ghosh, Shen Zheng, Robert Tamburo +7
Perceiving and autonomously navigating through work zones is a challenging and underexplored problem. Open datasets for this long-tailed scenario are scarce. We propose the ROADWor…
AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis
Khiem Vuong, Anurag Ghosh, Deva Ramanan +2
We explore the task of geometric reconstruction of images captured from a mixture of ground and aerial views. Current state-of-the-art learning-based approaches fail to handle the…