{"url":"/task/surface-normal-estimation","name":"Surface Normal Estimation","slug":"surface-normal-estimation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":96,"papers_with_code":46,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/nyuv2","name":"NYUv2","full_name":"NYU-Depth V2","num_papers_in_archive":986},{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/3d-ken-burns-dataset","name":"3D Ken Burns Dataset","full_name":"","num_papers_in_archive":4},{"url":"/dataset/futurehouse","name":"FutureHouse","full_name":"","num_papers_in_archive":3},{"url":"/dataset/carla2real","name":"CARLA2Real","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":46,"tagged_in_all":96,"items":[{"url":"/paper/predicting-depth-surface-normals-and-semantic","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","date":"2014-11-18","arxiv_id":"1411.4734","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/maintaining-natural-image-statistics-with-the","title":"Maintaining Natural Image Statistics with the Contextual Loss","date":"2018-03-13","arxiv_id":"1803.04626","repositories_listed":3,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/sapiens-foundation-for-human-vision-models","title":"Sapiens: Foundation for Human Vision Models","date":"2024-08-22","arxiv_id":"2408.12569","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/idisc-internal-discretization-for-monocular","title":"iDisc: Internal Discretization for Monocular Depth Estimation","date":"2023-04-13","arxiv_id":"2304.06334","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/a-large-scale-homography-benchmark","title":"A Large Scale Homography Benchmark","date":"2023-02-20","arxiv_id":"2302.09997","repositories_listed":2,"syntology":null},{"url":"/paper/cross-task-attention-mechanism-for-dense","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","date":"2022-06-17","arxiv_id":"2206.08927","repositories_listed":2,"syntology":null},{"url":"/paper/geonet-iterative-geometric-neural-network","title":"GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation","date":"2020-12-13","arxiv_id":"2012.06980","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-and-benchmarking-self-supervised","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","date":"2019-05-03","arxiv_id":"1905.01235","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-iterative-surface-normal","title":"Deep Iterative Surface Normal Estimation","date":"2019-04-15","arxiv_id":"1904.07172","repositories_listed":2,"syntology":null},{"url":"/paper/spherical-regression-learning-viewpoints","title":"Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres","date":"2019-04-10","arxiv_id":"1904.05404","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/lisu-a-dataset-and-method-for-lidar-surface-1","title":"LiSu: A Dataset and Method for LiDAR Surface Normal Estimation","date":"2025-03-11","arxiv_id":"2503.08601","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-geometric-estimation-of-depth-and","title":"Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images","date":"2024-11-04","arxiv_id":"2411.01749","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-image-conditional-diffusion","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","date":"2024-09-17","arxiv_id":"2409.11355","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_unverified":1,"n_pointer_only":17}},{"url":"/paper/metric3d-v2-a-versatile-monocular-geometric-1","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","date":"2024-03-22","arxiv_id":"2404.15506","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/diffusion-models-trained-with-large-data-are","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","date":"2024-03-10","arxiv_id":"2403.06090","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/rethinking-inductive-biases-for-surface","title":"Rethinking Inductive Biases for Surface Normal Estimation","date":"2024-03-01","arxiv_id":"2403.00712","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/polymax-general-dense-prediction-with-mask","title":"PolyMaX: General Dense Prediction with Mask Transformer","date":"2023-11-09","arxiv_id":"2311.05770","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tsp-transformer-task-specific-prompts-boosted","title":"TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding","date":"2023-11-06","arxiv_id":"2311.03427","repositories_listed":1,"syntology":null},{"url":"/paper/decodable-and-sample-invariant-continuous","title":"Decodable and Sample Invariant Continuous Object Encoder","date":"2023-10-31","arxiv_id":"2311.00187","repositories_listed":1,"syntology":null},{"url":"/paper/found-foot-optimization-with-uncertain","title":"FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Data","date":"2023-10-27","arxiv_id":"2310.18279","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-guided-transformer-for-multi-task","title":"Prompt Guided Transformer for Multi-Task Dense Prediction","date":"2023-07-28","arxiv_id":"2307.15362","repositories_listed":1,"syntology":null},{"url":"/paper/independent-component-alignment-for-multi-1","title":"Independent Component Alignment for Multi-Task Learning","date":"2023-05-30","arxiv_id":"2305.19000","repositories_listed":1,"syntology":null},{"url":"/paper/d2nt-a-high-performing-depth-to-normal","title":"D2NT: A High-Performing Depth-to-Normal Translator","date":"2023-04-24","arxiv_id":"2304.12031","repositories_listed":1,"syntology":null},{"url":"/paper/high-quality-rgb-d-reconstruction-via-multi","title":"High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF","date":"2022-10-21","arxiv_id":"2210.12202","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-meta-learning-learn-how-to-adapt","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","date":"2022-10-13","arxiv_id":"2210.06989","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/perspective-phase-angle-model-for","title":"Perspective Phase Angle Model for Polarimetric 3D Reconstruction","date":"2022-07-20","arxiv_id":"2207.09629","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/egocentric-scene-understanding-via-multimodal-1","title":"Egocentric Scene Understanding via Multimodal Spatial Rectifier","date":"2022-07-14","arxiv_id":"2207.07077","repositories_listed":1,"syntology":null},{"url":"/paper/mult-an-end-to-end-multitask-learning","title":"MulT: An End-to-End Multitask Learning Transformer","date":"2022-05-17","arxiv_id":"2205.08303","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/grit-general-robust-image-task-benchmark","title":"GRIT: General Robust Image Task Benchmark","date":"2022-04-28","arxiv_id":"2204.13653","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/inverted-pyramid-multi-task-transformer-for","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","date":"2022-03-15","arxiv_id":"2203.07997","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}