{"list":"other","total":69,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"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":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2104.10078","title":"UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction","created":"2021-04-20","cited_by_count":646},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470},{"id":"2306.03092","title":"Neuralangelo: High-Fidelity Neural Surface Reconstruction","created":"2023-06-05","cited_by_count":467},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2305.15347","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","created":"2023-05-24","cited_by_count":301},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1411.5908","title":"Understanding image representations by measuring their equivariance and equivalence","created":"2014-11-21","cited_by_count":243},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2003.10432","title":"Atlas: End-to-End 3D Scene Reconstruction from Posed Images","created":"2020-03-23","cited_by_count":206},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"2205.02836","title":"Neural 3D Scene Reconstruction with the Manhattan-world Assumption","created":"2022-05-05","cited_by_count":123},{"id":"2206.07850","title":"HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details","created":"2022-06-15","cited_by_count":121},{"id":"2305.15581","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","created":"2023-05-24","cited_by_count":120},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86},{"id":"2208.14743","title":"SimpleRecon: 3D Reconstruction Without 3D Convolutions","created":"2022-08-31","cited_by_count":83},{"id":"2205.12955","title":"Neural 3D Reconstruction in the Wild","created":"2022-05-25","cited_by_count":79},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59},{"id":"2405.12979","title":"OmniGlue: Generalizable Feature Matching with Foundation Model Guidance","created":"2024-05-21","cited_by_count":56},{"id":"2311.17024","title":"Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features","created":"2023-11-28","cited_by_count":55},{"id":"2205.04502","title":"Multiview Stereo with Cascaded Epipolar RAFT","created":"2022-05-09","cited_by_count":51},{"id":"2412.06016","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","created":"2024-12-08","cited_by_count":44},{"id":"2308.16777","title":"Ref-Diff: Zero-shot Referring Image Segmentation with Generative Models","created":"2023-08-31","cited_by_count":33},{"id":"2103.01530","title":"A Pose-only Solution to Visual Reconstruction and Navigation","created":"2021-03-02","cited_by_count":20},{"id":"2308.05733","title":"FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models","created":"2023-08-10","cited_by_count":17},{"id":"2406.02495","title":"GenS: Generalizable Neural Surface Reconstruction from Multi-View Images","created":"2024-06-04","cited_by_count":15},{"id":"2008.12295","title":"Reducing Drift in Structure From Motion Using Extended Features","created":"2020-08-27","cited_by_count":10},{"id":"2307.09160","title":"Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells","created":"2023-07-18","cited_by_count":8}],"next_cursor":null}