{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/focus-is-all-you-need-loss-functions-for","title":"Focus Is All You Need: Loss Functions For Event-based Vision","arxiv_id":"1904.07235","date":"2019-04-15","proceeding":"CVPR 2019 6","authors":["Guillermo Gallego","Mathias Gehrig","Davide Scaramuzza"],"abstract":"Event cameras are novel vision sensors that output pixel-level brightness\nchanges (\"events\") instead of traditional video frames. These asynchronous\nsensors offer several advantages over traditional cameras, such as, high\ntemporal resolution, very high dynamic range, and no motion blur. To unlock the\npotential of such sensors, motion compensation methods have been recently\nproposed. We present a collection and taxonomy of twenty two objective\nfunctions to analyze event alignment in motion compensation approaches (Fig.\n1). We call them Focus Loss Functions since they have strong connections with\nfunctions used in traditional shape-from-focus applications. The proposed loss\nfunctions allow bringing mature computer vision tools to the realm of event\ncameras. We compare the accuracy and runtime performance of all loss functions\non a publicly available dataset, and conclude that the variance, the gradient\nand the Laplacian magnitudes are among the best loss functions. The\napplicability of the loss functions is shown on multiple tasks: rotational\nmotion, depth and optical flow estimation. The proposed focus loss functions\nallow to unlock the outstanding properties of event cameras.","url_abs":"http://arxiv.org/abs/1904.07235v1","url_pdf":"http://arxiv.org/pdf/1904.07235v1.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":"focus-is-all-you-need-loss-functions-for","repo_url":"https://github.com/tub-rip/dvs_global_flow_skeleton","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"event-based-vision","task_name":"Event-based vision"},{"task_slug":"motion-compensation","task_name":"Motion Compensation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.07235","atlas_url":"https://app.syntology.ai/?focus=1904.07235","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1904.07235"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.07235\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.07235"},"call":"get_concepts_for_paper(arxiv_id=\"1904.07235\")"}],"by_repo":[{"repo":"tub-rip/dvs_global_flow_skeleton","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6b9bad41ba4b431411317d188683d78d19a11817b532d37e7a082bc5b8aebfaa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}