{"list":"other","total":81,"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"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":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"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":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"id":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2011.03277","title":"Modular Primitives for High-Performance Differentiable Rendering","created":"2020-11-06","cited_by_count":441},{"id":"2404.07191","title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","created":"2024-04-10","cited_by_count":433},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288},{"id":"2311.07885","title":"One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion","created":"2023-11-14","cited_by_count":283},{"id":"2203.13333","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","created":"2022-03-24","cited_by_count":281},{"id":"2312.02201","title":"ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation","created":"2023-12-02","cited_by_count":257},{"id":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"2303.13508","title":"DreamBooth3D: Subject-Driven Text-to-3D Generation","created":"2023-03-23","cited_by_count":235},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216},{"id":"2311.09217","title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","created":"2023-11-15","cited_by_count":214},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168},{"id":"2310.16818","title":"DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior","created":"2023-10-25","cited_by_count":158},{"id":"2303.11306","title":"Localizing Object-level Shape Variations with Text-to-Image Diffusion Models","created":"2023-03-20","cited_by_count":142},{"id":"2308.12469","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","created":"2023-08-23","cited_by_count":131},{"id":"1812.02725","title":"Visual Object Networks: Image Generation with Disentangled 3D Representation","created":"2018-12-06","cited_by_count":124},{"id":"1810.05591","title":"PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention","created":"2018-10-12","cited_by_count":105},{"id":"1908.01491","title":"Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation","created":"2019-08-05","cited_by_count":103},{"id":"2103.00762","title":"NeuTex: Neural Texture Mapping for Volumetric Neural Rendering","created":"2021-03-01","cited_by_count":98},{"id":"2401.18084","title":"Binding Touch to Everything: Learning Unified Multimodal Tactile Representations","created":"2024-01-31","cited_by_count":95},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89},{"id":"2004.04180","title":"Leveraging 2D Data to Learn Textured 3D Mesh Generation","created":"2020-04-08","cited_by_count":69},{"id":"1906.06322","title":"Connecting Touch and Vision via Cross-Modal Prediction","created":"2019-06-14","cited_by_count":66},{"id":"2204.02411","title":"Texturify: Generating Textures on 3D Shape Surfaces","created":"2022-04-05","cited_by_count":65},{"id":"2003.02050","title":"Learning to Transfer Texture from Clothing Images to 3D Humans","created":"2020-03-04","cited_by_count":58},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56},{"id":"1803.00628","title":"GelSlim: A High-Resolution, Compact, Robust, and Calibrated Tactile-sensing Finger","created":"2018-03-01","cited_by_count":52},{"id":"2007.03778","title":"3D Shape Reconstruction from Vision and Touch","created":"2020-07-07","cited_by_count":42},{"id":"2306.07473","title":"3D molecule generation by denoising voxel grids","created":"2023-06-13","cited_by_count":40},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37},{"id":"2306.10533","title":"Point-Cloud Completion with Pretrained Text-to-image Diffusion Models","created":"2023-06-18","cited_by_count":37},{"id":"2308.02874","title":"Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation","created":"2023-08-05","cited_by_count":36},{"id":"2106.08851","title":"GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger","created":"2021-06-16","cited_by_count":34},{"id":"2107.09584","title":"Active 3D Shape Reconstruction from Vision and Touch","created":"2021-07-20","cited_by_count":34},{"id":"2108.09936","title":"Voxel-based Network for Shape Completion by Leveraging Edge Generation","created":"2021-08-23","cited_by_count":32},{"id":"1808.03247","title":"3D Shape Perception from Monocular Vision, Touch, and Shape Priors","created":"2018-08-09","cited_by_count":31},{"id":"2109.09884","title":"ShapeMap 3-D: Efficient shape mapping through dense touch and vision","created":"2021-09-20","cited_by_count":31},{"id":"2405.04534","title":"Tactile-Augmented Radiance Fields","created":"2024-05-07","cited_by_count":26},{"id":"2403.09875","title":"Touch-GS: Visual-Tactile Supervised 3D Gaussian Splatting","created":"2024-03-14","cited_by_count":16},{"id":"2311.12602","title":"TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensing","created":"2023-11-21","cited_by_count":15},{"id":"2403.20275","title":"Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces","created":"2024-03-29","cited_by_count":12},{"id":"2305.03040","title":"TUVF: Learning Generalizable Texture UV Radiance Fields","created":"2023-05-04","cited_by_count":9},{"id":"2305.03051","title":"Controllable Visual-Tactile Synthesis","created":"2023-05-04","cited_by_count":8}],"next_cursor":null}