{"list":"other","total":68,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"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":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2112.00724","title":"RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs","created":"2021-12-01","cited_by_count":615},{"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":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2012.03918","title":"NeRD: Neural Reflectance Decomposition from Image Collections","created":"2020-12-07","cited_by_count":449},{"id":"2111.12503","title":"Extracting Triangular 3D Models, Materials, and Lighting From Images","created":"2021-11-24","cited_by_count":366},{"id":"2104.00674","title":"PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting","created":"2021-04-01","cited_by_count":335},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2110.14373","title":"Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition","created":"2021-10-27","cited_by_count":205},{"id":"1905.02722","title":"Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image","created":"2019-05-07","cited_by_count":203},{"id":"2008.03824","title":"Neural Reflectance Fields for Appearance Acquisition","created":"2020-08-09","cited_by_count":196},{"id":"2204.06837","title":"Modeling Indirect Illumination for Inverse Rendering","created":"2022-04-14","cited_by_count":168},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2312.03704","title":"Relightable Gaussian Codec Avatars","created":"2023-12-06","cited_by_count":127},{"id":"1810.09718","title":"Single-Image SVBRDF Capture with a Rendering-Aware Deep Network","created":"2018-10-23","cited_by_count":116},{"id":"1901.02453","title":"Neural Inverse Rendering of an Indoor Scene from a Single Image","created":"2019-01-08","cited_by_count":101},{"id":"2007.09892","title":"Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images","created":"2020-07-20","cited_by_count":98},{"id":"2501.06336","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","created":"2025-01-10","cited_by_count":95},{"id":"2205.15768","title":"SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections","created":"2022-05-31","cited_by_count":89},{"id":"2312.11360","title":"Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering","created":"2023-12-18","cited_by_count":84},{"id":"2211.03017","title":"Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing","created":"2022-11-06","cited_by_count":78},{"id":"2303.17147","title":"NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimation","created":"2023-03-30","cited_by_count":74},{"id":"2312.12274","title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","created":"2023-12-19","cited_by_count":73},{"id":"1804.05790","title":"Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image","created":"2018-04-16","cited_by_count":66},{"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":"2003.12642","title":"Deep 3D Capture: Geometry and Reflectance from Sparse Multi-View Images","created":"2020-03-27","cited_by_count":65},{"id":"2303.13022","title":"ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting","created":"2023-03-23","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":"2004.00403","title":"Two-shot Spatially-varying BRDF and Shape Estimation","created":"2020-04-01","cited_by_count":59},{"id":"1906.07370","title":"Neural Illumination: Lighting Prediction for Indoor Environments","created":"2019-06-18","cited_by_count":58},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56},{"id":"2310.16044","title":"Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark","created":"2023-10-24","cited_by_count":51},{"id":"1906.11557","title":"Flexible SVBRDF Capture with a Multi-Image Deep Network","created":"2019-06-27","cited_by_count":50},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50},{"id":"2501.04689","title":"SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images","created":"2025-01-08","cited_by_count":42},{"id":"2102.11861","title":"Generative Modelling of BRDF Textures from Flash Images","created":"2021-02-23","cited_by_count":35},{"id":"2012.06777","title":"Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces","created":"2020-12-12","cited_by_count":33},{"id":"2312.14198","title":"ZeroShape: Regression-based Zero-shot Shape Reconstruction","created":"2023-12-21","cited_by_count":30},{"id":"2311.17060","title":"Material Palette: Extraction of Materials from a Single Image","created":"2023-11-28","cited_by_count":28},{"id":"2007.03059","title":"Guided Fine-Tuning for Large-Scale Material Transfer","created":"2020-07-06","cited_by_count":27},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25},{"id":"2402.05919","title":"Collaborative Control for Geometry-Conditioned PBR Image Generation","created":"2024-02-08","cited_by_count":22},{"id":"2401.07727","title":"HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation","created":"2024-01-15","cited_by_count":21},{"id":"2401.10171","title":"SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild","created":"2024-01-18","cited_by_count":18},{"id":"2010.04143","title":"Deep SVBRDF Estimation on Real Materials","created":"2020-10-08","cited_by_count":15},{"id":"2203.12613","title":"Hybrid Mesh-neural Representation for 3D Transparent Object Reconstruction","created":"2022-03-23","cited_by_count":15},{"id":"2206.03858","title":"Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Prior","created":"2022-06-07","cited_by_count":12},{"id":"1910.05148","title":"Single Image BRDF Parameter Estimation with a Conditional Adversarial Network","created":"2019-10-11","cited_by_count":6},{"id":"2105.13012","title":"Passing Multi-Channel Material Textures to a 3-Channel Loss","created":"2021-05-27","cited_by_count":6},{"id":"2311.09361","title":"RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Prior","created":"2023-11-15","cited_by_count":6}],"next_cursor":null}