{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ghost-free-high-dynamic-range-imaging-with","title":"Ghost-free High Dynamic Range Imaging with Context-aware Transformer","arxiv_id":"2208.05114","date":"2022-08-10","proceeding":null,"authors":["Zhen Liu","Yinglong Wang","Bing Zeng","Shuaicheng Liu"],"abstract":"High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based methods are typically prone to producing ghosting artifacts and intensity distortions in the presence of large motion and severe saturation. In this paper, we propose a novel Context-Aware Vision Transformer (CA-ViT) for ghost-free high dynamic range imaging. The CA-ViT is designed as a dual-branch architecture, which can jointly capture both global and local dependencies. Specifically, the global branch employs a window-based Transformer encoder to model long-range object movements and intensity variations to solve ghosting. For the local branch, we design a local context extractor (LCE) to capture short-range image features and use the channel attention mechanism to select informative local details across the extracted features to complement the global branch. By incorporating the CA-ViT as basic components, we further build the HDR-Transformer, a hierarchical network to reconstruct high-quality ghost-free HDR images. Extensive experiments on three benchmark datasets show that our approach outperforms state-of-the-art methods qualitatively and quantitatively with considerably reduced computational budgets. Codes are available at https://github.com/megvii-research/HDR-Transformer","url_abs":"https://arxiv.org/abs/2208.05114v1","url_pdf":"https://arxiv.org/pdf/2208.05114v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ghost-free-high-dynamic-range-imaging-with","repo_url":"https://github.com/megvii-research/hdr-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ghost-free-high-dynamic-range-imaging-with","repo_url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HDR-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"ghost-free-high-dynamic-range-imaging-with","repo_url":"https://github.com/Mind23-2/MindCode-3/tree/main/HDR-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.05114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05114"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HDR-Transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megvii-research/hdr-transformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HDR-Transformer","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/megvii-research/HDR-Transformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a7b3ecd01fd42f74","entry":"batch_psnr","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"loss/losses.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/loss/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7b3ecd01fd42f74"}},{"code_sha256_prefix":"bbfce380e2b91f46","entry":"fetch_transform","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"dataset/transformations.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/dataset/transformations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bbfce380e2b91f46"}},{"code_sha256_prefix":"894888101816dfd4","entry":"flip_sample","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"dataset/gen_crop_data.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/dataset/gen_crop_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"894888101816dfd4"}},{"code_sha256_prefix":"48b29b7d5a67511f","entry":"get_croped_data_per_scene","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"dataset/gen_crop_data.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/dataset/gen_crop_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48b29b7d5a67511f"}},{"code_sha256_prefix":"6084c0eb4c908f20","entry":"loss_meter_manager_intial","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"common/utils.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/common/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6084c0eb4c908f20"}},{"code_sha256_prefix":"235ee34370d7c9de","entry":"rotate_sample","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"dataset/gen_crop_data.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/dataset/gen_crop_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"235ee34370d7c9de"}},{"code_sha256_prefix":"73879546dbb5b1b1","entry":"window_partition","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"model/hdr_transformer.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/model/hdr_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73879546dbb5b1b1"}},{"code_sha256_prefix":"d8fbbb48e7a9bf31","entry":"window_reverse","repo":"megvii-research/HDR-Transformer","repo_kind":"official","path":"model/hdr_transformer.py","file_url":"https://github.com/megvii-research/HDR-Transformer/blob/HEAD/model/hdr_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8fbbb48e7a9bf31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}