{"total":19,"rows":[{"id":"2604.08626","title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","created":"2026-04-09","cited_by_count":14,"area":null},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2602.23893","title":"AoE: Always-on Egocentric Human Video Collection for Embodied AI","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2608.30821","title":"Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2606.16960","title":"SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2608.16984","title":"PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2605.26230","title":"Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.27367","title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.02551","title":"AFUN: Towards an Affordance Foundation Model for Functionality Understanding","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.11326","title":"DarkVGGT: Seeing Through Darkness Using Thermal Geometry","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.05250","title":"Streaming Neural Speech Codecs through Time-Invariant Representations","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08765","title":"Enhancing In-context Panoramic Generation via Geometric-aware Pretraining","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.32323","title":"FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34346","title":"E-WAVE: Event-based Continuous Optical Flow via Warping-Aligned Visual Encoding","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35575","title":"F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.03015","title":"OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15287","title":"ASM-6D: Fast Certified Pose-Shape Inference with Complete Correspondence Flow Maps","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}