{"list":"other","total":60,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2412.06264","title":"Flow Matching Guide and Code","created":"2024-12-09","cited_by_count":301},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"2311.17977","title":"GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces","created":"2023-11-29","cited_by_count":252},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"1908.01210","title":"Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer","created":"2019-08-03","cited_by_count":221},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"id":"1708.01749","title":"SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","created":"2017-08-05","cited_by_count":128},{"id":"1910.02550","title":"ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation","created":"2019-10-06","cited_by_count":124},{"id":"2402.17113","title":"Transparent Image Layer Diffusion using Latent Transparency","created":"2024-02-27","cited_by_count":114},{"id":"2412.05435","title":"UniScene: Unified Occupancy-centric Driving Scene Generation","created":"2024-12-06","cited_by_count":106},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99},{"id":"1903.03273","title":"FastDepth: Fast Monocular Depth Estimation on Embedded Systems","created":"2019-03-08","cited_by_count":94},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74},{"id":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"1810.01849","title":"SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation","created":"2018-10-03","cited_by_count":64},{"id":"2310.17274","title":"cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation","created":"2023-10-26","cited_by_count":52},{"id":"1807.08696","title":"PS-FCN: A Flexible Learning Framework for Photometric Stereo","created":"2018-07-23","cited_by_count":51},{"id":"2208.03792","title":"Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects","created":"2022-08-07","cited_by_count":50},{"id":"1903.07366","title":"Self-calibrating Deep Photometric Stereo Networks","created":"2019-03-18","cited_by_count":47},{"id":"2203.03890","title":"ClearPose: Large-scale Transparent Object Dataset and Benchmark","created":"2022-03-08","cited_by_count":46},{"id":"2411.09153","title":"VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation","created":"2024-11-14","cited_by_count":46},{"id":"2304.10080","title":"NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering","created":"2023-04-20","cited_by_count":41},{"id":"2307.15052","title":"Learning Depth Estimation for Transparent and Mirror Surfaces","created":"2023-07-27","cited_by_count":34},{"id":"2411.19189","title":"Video Depth without Video Models","created":"2024-11-28","cited_by_count":29},{"id":"2404.16306","title":"TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models","created":"2024-04-25","cited_by_count":25},{"id":"2502.12231","title":"PUGS: Zero-shot Physical Understanding with Gaussian Splatting","created":"2025-02-17","cited_by_count":24},{"id":"2303.13959","title":"Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion","created":"2023-03-24","cited_by_count":22},{"id":"2309.05098","title":"3D Implicit Transporter for Temporally Consistent Keypoint Discovery","created":"2023-09-10","cited_by_count":20},{"id":"2401.04325","title":"RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale","created":"2024-01-09","cited_by_count":20},{"id":"2407.05254","title":"GaussReg: Fast 3D Registration with Gaussian Splatting","created":"2024-07-07","cited_by_count":19},{"id":"2506.03079","title":"ORV: 4D Occupancy-centric Robot Video Generation","created":"2025-06-03","cited_by_count":17},{"id":"2309.13039","title":"NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields","created":"2023-09-22","cited_by_count":16},{"id":"2307.05016","title":"TRansPose: Large-Scale Multispectral Dataset for Transparent Object","created":"2023-07-11","cited_by_count":15},{"id":"2506.05280","title":"Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting","created":"2025-06-05","cited_by_count":15},{"id":"1611.02174","title":"Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation","created":"2016-10-17","cited_by_count":14},{"id":"2409.14365","title":"D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation","created":"2024-09-22","cited_by_count":14},{"id":"2504.07093","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","created":"2025-04-09","cited_by_count":14},{"id":"2306.12681","title":"One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception","created":"2023-06-22","cited_by_count":13},{"id":"2405.05648","title":"ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera","created":"2024-05-09","cited_by_count":9},{"id":"2310.16750","title":"Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots","created":"2023-10-25","cited_by_count":8},{"id":"2502.14616","title":"Monocular Depth Estimation and Segmentation for Transparent Object with Iterative Semantic and Geometric Fusion","created":"2025-02-20","cited_by_count":8},{"id":"2308.10569","title":"Real-time Monocular Depth Estimation on Embedded Systems","created":"2023-08-21","cited_by_count":6},{"id":"1809.07677","title":"Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurements","created":"2018-09-20","cited_by_count":5},{"id":"2411.18276","title":"GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation","created":"2024-11-27","cited_by_count":5},{"id":"2105.07468","title":"TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction","created":"2021-05-16","cited_by_count":4},{"id":"2404.07545","title":"Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversion","created":"2024-04-11","cited_by_count":4},{"id":"2402.04883","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","created":"2024-02-07","cited_by_count":3},{"id":"2402.14354","title":"GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints","created":"2024-02-22","cited_by_count":3},{"id":"2507.23483","title":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion","created":"2025-07-31","cited_by_count":2}],"next_cursor":null}