{"list":"other","total":91,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2403.06976","title":"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion","created":"2024-03-11","cited_by_count":202},{"id":"2007.10247","title":"Learning Joint Spatial-Temporal Transformations for Video Inpainting","created":"2020-07-20","cited_by_count":163},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144},{"id":"2408.16767","title":"ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model","created":"2024-08-29","cited_by_count":143},{"id":"1903.11444","title":"Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving","created":"2019-03-27","cited_by_count":137},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"1905.02884","title":"Deep Flow-Guided Video Inpainting","created":"2019-05-08","cited_by_count":116},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"1905.01639","title":"Deep Video Inpainting","created":"2019-05-05","cited_by_count":109},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108},{"id":"2303.02091","title":"Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement","created":"2023-03-03","cited_by_count":106},{"id":"2009.01835","title":"Flow-edge Guided Video Completion","created":"2020-09-03","cited_by_count":104},{"id":"2103.12340","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","created":"2021-03-23","cited_by_count":104},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"2406.16862","title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","created":"2024-06-24","cited_by_count":87},{"id":"2312.03816","title":"AVID: Any-Length Video Inpainting with Diffusion Model","created":"2023-12-06","cited_by_count":82},{"id":"2403.13788","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","created":"2024-03-20","cited_by_count":76},{"id":"2012.13755","title":"Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving","created":"2020-12-26","cited_by_count":73},{"id":"2401.14398","title":"pix2gestalt: Amodal Segmentation by Synthesizing Wholes","created":"2024-01-25","cited_by_count":70},{"id":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66},{"id":"1604.08202","title":"Amodal Instance Segmentation","created":"2016-04-27","cited_by_count":63},{"id":"1804.08864","title":"Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation","created":"2018-04-24","cited_by_count":62},{"id":"1908.11587","title":"Copy-and-Paste Networks for Deep Video Inpainting","created":"2019-08-30","cited_by_count":58},{"id":"2312.17247","title":"Amodal Ground Truth and Completion in the Wild","created":"2023-12-28","cited_by_count":45},{"id":"2403.12010","title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","created":"2024-03-18","cited_by_count":45},{"id":"2404.16666","title":"PhyRecon: Physically Plausible Neural Scene Reconstruction","created":"2024-04-25","cited_by_count":45},{"id":"2406.03697","title":"Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction","created":"2024-06-06","cited_by_count":45},{"id":"2312.15540","title":"Amodal Completion via Progressive Mixed Context Diffusion","created":"2023-12-24","cited_by_count":38},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37},{"id":"2009.05721","title":"Short-Term and Long-Term Context Aggregation Network for Video Inpainting","created":"2020-09-12","cited_by_count":35},{"id":"2401.10226","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","created":"2024-01-18","cited_by_count":33},{"id":"2108.06765","title":"Occlusion-Aware Video Object Inpainting","created":"2021-08-15","cited_by_count":30},{"id":"2305.15727","title":"POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference","created":"2023-05-25","cited_by_count":30},{"id":"2308.16825","title":"Coarse-to-Fine Amodal Segmentation with Shape Prior","created":"2023-08-31","cited_by_count":29},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28},{"id":"2404.17521","title":"Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations","created":"2024-04-26","cited_by_count":24},{"id":"2403.11878","title":"InTeX: Interactive Text-to-texture Synthesis via Unified Depth-aware Inpainting","created":"2024-03-18","cited_by_count":22},{"id":"1509.08147","title":"Amodal Completion and Size Constancy in Natural Scenes","created":"2015-09-27","cited_by_count":21},{"id":"2412.04623","title":"Using Diffusion Priors for Video Amodal Segmentation","created":"2024-12-05","cited_by_count":16},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15},{"id":"2210.12733","title":"Self-supervised Amodal Video Object Segmentation","created":"2022-10-23","cited_by_count":14},{"id":"2406.02461","title":"RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting","created":"2024-06-04","cited_by_count":14},{"id":"2408.06697","title":"SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields","created":"2024-08-13","cited_by_count":12},{"id":"2412.11457","title":"MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes","created":"2024-12-16","cited_by_count":10},{"id":"2309.13248","title":"Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation","created":"2023-09-23","cited_by_count":9}],"next_cursor":null}