{"total":22,"rows":[{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125,"area":null},{"id":"2206.13597","title":"NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors","created":"2022-06-27","cited_by_count":125,"area":null},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116,"area":null},{"id":"2112.11377","title":"Shape from Polarization for Complex Scenes in the Wild","created":"2021-12-21","cited_by_count":53,"area":null},{"id":"2210.03676","title":"IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty","created":"2022-10-07","cited_by_count":30,"area":null},{"id":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26,"area":null},{"id":"2406.11711","title":"OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2107.14599","title":"SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection","created":"2021-07-30","cited_by_count":23,"area":null},{"id":"2210.01044","title":"SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image","created":"2022-10-03","cited_by_count":19,"area":null},{"id":"2207.07077","title":"Egocentric Scene Understanding via Multimodal Spatial Rectifier","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2210.06853","title":"NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2211.12400","title":"DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair","created":"2022-11-22","cited_by_count":5,"area":null},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2310.09092","title":"iPUNet:Iterative Cross Field Guided Point Cloud Upsampling","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2309.16646","title":"Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2310.11184","title":"Sparse Multi-Object Render-and-Compare","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2408.09336","title":"Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration","created":"2024-08-18","cited_by_count":3,"area":null},{"id":"2103.03510","title":"Variational Structured Attention Networks for Deep Visual Representation Learning","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2403.15448","title":"What is Wrong with End-to-End Learning for Phase Retrieval?","created":"2024-03-18","cited_by_count":2,"area":null}],"next_cursor":null}