{"list":"other","total":79,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2012.12247","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","created":"2020-12-22","cited_by_count":471},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"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":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2012.09790","title":"Neural Radiance Flow for 4D View Synthesis and Video Processing","created":"2020-12-17","cited_by_count":270},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"1906.02634","title":"Scaling Autoregressive Video Models","created":"2019-06-06","cited_by_count":190},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2004.01294","title":"Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera","created":"2020-04-02","cited_by_count":166},{"id":"2202.08614","title":"Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time","created":"2022-02-17","cited_by_count":165},{"id":"2104.14786","title":"Editable Free-viewpoint Video Using a Layered Neural Representation","created":"2021-04-30","cited_by_count":148},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"2303.12218","title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","created":"2023-03-21","cited_by_count":101},{"id":"2004.02788","title":"Self-Supervised Scene De-occlusion","created":"2020-04-06","cited_by_count":96},{"id":"2302.14816","title":"Monocular Depth Estimation using Diffusion Models","created":"2023-02-28","cited_by_count":87},{"id":"2105.05994","title":"Neural Trajectory Fields for Dynamic Novel View Synthesis","created":"2021-05-12","cited_by_count":86},{"id":"2401.14398","title":"pix2gestalt: Amodal Segmentation by Synthesizing Wholes","created":"2024-01-25","cited_by_count":70},{"id":"2005.13532","title":"4D Visualization of Dynamic Events from Unconstrained Multi-View Videos","created":"2020-05-27","cited_by_count":66},{"id":"1703.10239","title":"SeGAN: Segmenting and Generating the Invisible","created":"2017-03-29","cited_by_count":60},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60},{"id":"2312.08885","title":"SceneWiz3D: Towards Text-guided 3D Scene Composition","created":"2023-12-13","cited_by_count":54},{"id":"2306.08731","title":"EPIC Fields: Marrying 3D Geometry and Video Understanding","created":"2023-06-14","cited_by_count":49},{"id":"2012.00914","title":"MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection","created":"2020-12-02","cited_by_count":44},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32},{"id":"2003.10469","title":"Learning Object Permanence from Video","created":"2020-03-23","cited_by_count":30},{"id":"2204.01784","title":"Object Permanence Emerges in a Random Walk along Memory","created":"2022-04-04","cited_by_count":18},{"id":"2401.05583","title":"Diffusion Priors for Dynamic View Synthesis from Monocular Videos","created":"2024-01-10","cited_by_count":18},{"id":"2204.10916","title":"Revealing Occlusions with 4D Neural Fields","created":"2022-04-22","cited_by_count":17},{"id":"2305.03052","title":"Tracking through Containers and Occluders in the Wild","created":"2023-05-04","cited_by_count":15},{"id":"2207.02186","title":"NeuralPassthrough: Learned Real-Time View Synthesis for VR","created":"2022-07-05","cited_by_count":8}],"next_cursor":null}