{"list":"other","total":86,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"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":"2112.07945","title":"Efficient Geometry-aware 3D Generative Adversarial Networks","created":"2021-12-15","cited_by_count":1205},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843},{"id":"1905.05172","title":"PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization","created":"2019-05-13","cited_by_count":818},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"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":"2212.00774","title":"Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation","created":"2022-12-01","cited_by_count":597},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2302.07121","title":"Universal Guidance for Diffusion Models","created":"2023-02-14","cited_by_count":437},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"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":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2007.03858","title":"PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction","created":"2020-07-08","cited_by_count":231},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"id":"1905.06292","title":"3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions","created":"2019-05-15","cited_by_count":173},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"2304.00916","title":"DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models","created":"2023-04-03","cited_by_count":154},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2210.04888","title":"EVA3D: Compositional 3D Human Generation from 2D Image Collections","created":"2022-10-10","cited_by_count":111},{"id":"2308.10899","title":"TADA! Text to Animatable Digital Avatars","created":"2023-08-21","cited_by_count":110},{"id":"2108.10842","title":"imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose","created":"2021-08-24","cited_by_count":103},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102},{"id":"1804.06023","title":"DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor","created":"2018-04-17","cited_by_count":95},{"id":"2112.02308","title":"MoFaNeRF: Morphable Facial Neural Radiance Field","created":"2021-12-04","cited_by_count":94},{"id":"2304.13348","title":"TextDeformer: Geometry Manipulation using Text Guidance","created":"2023-04-26","cited_by_count":94},{"id":"2303.13071","title":"PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\\circ}$","created":"2023-03-23","cited_by_count":93},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92},{"id":"2310.01406","title":"HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation","created":"2023-10-02","cited_by_count":88},{"id":"2303.17606","title":"AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Control","created":"2023-03-30","cited_by_count":84},{"id":"2305.12529","title":"DreamWaltz: Make a Scene with Complex 3D Animatable Avatars","created":"2023-05-21","cited_by_count":82},{"id":"2312.16693","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","created":"2023-12-27","cited_by_count":70},{"id":"2203.14622","title":"Towards Implicit Text-Guided 3D Shape Generation","created":"2022-03-28","cited_by_count":68},{"id":"2308.03610","title":"AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose","created":"2023-08-07","cited_by_count":60},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55},{"id":"2310.11784","title":"Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts","created":"2023-10-18","cited_by_count":52},{"id":"2406.09377","title":"GGHead: Fast and Generalizable 3D Gaussian Heads","created":"2024-06-13","cited_by_count":51},{"id":"1903.10384","title":"MeshGAN: Non-linear 3D Morphable Models of Faces","created":"2019-03-25","cited_by_count":39},{"id":"2309.07125","title":"Text-Guided Generation and Editing of Compositional 3D Avatars","created":"2023-09-13","cited_by_count":39},{"id":"2306.09864","title":"AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation","created":"2023-06-16","cited_by_count":37},{"id":"2502.08244","title":"FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis","created":"2025-02-12","cited_by_count":37},{"id":"2312.05295","title":"Disentangled Clothed Avatar Generation from Text Descriptions","created":"2023-12-08","cited_by_count":33},{"id":"2411.15604","title":"FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video","created":"2024-11-23","cited_by_count":32},{"id":"2303.13273","title":"TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision","created":"2023-03-23","cited_by_count":28},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28},{"id":"2410.10802","title":"Boosting Camera Motion Control for Video Diffusion Transformers","created":"2024-10-14","cited_by_count":20},{"id":"2404.01241","title":"StructLDM: Structured Latent Diffusion for 3D Human Generation","created":"2024-04-01","cited_by_count":17},{"id":"2108.02931","title":"Detailed Avatar Recovery from Single Image","created":"2021-08-06","cited_by_count":16},{"id":"2303.01311","title":"Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation","created":"2023-03-02","cited_by_count":15},{"id":"2405.19203","title":"$E^{3}$Gen: Efficient, Expressive and Editable Avatars Generation","created":"2024-05-29","cited_by_count":10},{"id":"2408.00296","title":"Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360{\\deg}","created":"2024-08-01","cited_by_count":9},{"id":"2405.00954","title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","created":"2024-05-02","cited_by_count":5},{"id":"2410.01226","title":"Towards Native Generative Model for 3D Head Avatar","created":"2024-10-02","cited_by_count":5},{"id":"2411.15205","title":"DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh","created":"2024-11-20","cited_by_count":5}],"next_cursor":null}