{"list":"other","total":75,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"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":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"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":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"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":"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":"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":"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":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"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":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"2309.16585","title":"Text-to-3D using Gaussian Splatting","created":"2023-09-28","cited_by_count":299},{"id":"2311.11284","title":"LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching","created":"2023-11-19","cited_by_count":290},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"2304.12439","title":"TextMesh: Generation of Realistic 3D Meshes From Text Prompts","created":"2023-04-24","cited_by_count":135},{"id":"2101.07296","title":"Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias","created":"2021-01-18","cited_by_count":118},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2305.18766","title":"HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance","created":"2023-05-30","cited_by_count":110},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109},{"id":"1612.00814","title":"Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision","created":"2016-12-01","cited_by_count":106},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87},{"id":"2411.00238","title":"Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem","created":"2024-10-31","cited_by_count":75},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74},{"id":"2407.02445","title":"Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials","created":"2024-07-02","cited_by_count":66},{"id":"2310.10343","title":"ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion","created":"2023-10-16","cited_by_count":65},{"id":"2408.00653","title":"SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement","created":"2024-08-01","cited_by_count":65},{"id":"2402.17678","title":"CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention","created":"2024-02-27","cited_by_count":64},{"id":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61},{"id":"2403.01807","title":"ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models","created":"2024-03-04","cited_by_count":57},{"id":"2403.15385","title":"LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis","created":"2024-03-22","cited_by_count":39},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37},{"id":"2012.12352","title":"Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks","created":"2020-12-22","cited_by_count":34},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32},{"id":"2401.11067","title":"Make-A-Shape: a Ten-Million-scale 3D Shape Model","created":"2024-01-20","cited_by_count":25},{"id":"2409.17106","title":"Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts","created":"2024-09-25","cited_by_count":23},{"id":"2312.03611","title":"DreamComposer: Controllable 3D Object Generation via Multi-View Conditions","created":"2023-12-06","cited_by_count":18},{"id":"2409.14677","title":"Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections","created":"2024-09-23","cited_by_count":16},{"id":"2405.09431","title":"A Survey On Text-to-3D Contents Generation In The Wild","created":"2024-05-15","cited_by_count":14},{"id":"2406.05649","title":"GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement","created":"2024-06-09","cited_by_count":14},{"id":"2410.00890","title":"Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation","created":"2024-10-01","cited_by_count":12},{"id":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10},{"id":"2410.20723","title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians","created":"2024-10-28","cited_by_count":10},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9},{"id":"2405.09874","title":"Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion","created":"2024-05-16","cited_by_count":9},{"id":"2312.00085","title":"X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation","created":"2023-11-30","cited_by_count":7},{"id":"2212.12952","title":"Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program","created":"2022-12-25","cited_by_count":6},{"id":"2311.11477","title":"What's left can't be right -- The remaining positional incompetence of contrastive vision-language models","created":"2023-11-20","cited_by_count":6},{"id":"2406.16695","title":"Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling","created":"2024-06-24","cited_by_count":6}],"next_cursor":null}